Journal articles: 'SNN'

1

Novy, Diane. "Effectiveness of Splanchnic Nerve Neurolysis for Targeting Location of Cancer Pain: Using the Pain Drawing as an Outcome Variable." July 2016 6;19, no. 6;7 (July 14, 2016): 397–403. http://dx.doi.org/10.36076/ppj/2016.19.397.

Full text

Abstract:

The effectiveness of splanchnic nerve neurolysis (SNN) for cancer-related abdominal pain has been investigated using numeric pain intensity rating as an outcome variable. The outcome variable in this study used the grid method for obtaining a targeted pain drawing score on 60 patients with pain from pancreatic or gastro-intestinal primary cancers or metastatic disease to the abdominal region. Results demonstrate excellent inter-rater agreement (intra-class correlation [ICC] coefficient at pre-SNN = 0.97 and ICC at within one month post-SNN = 0.98) for the grid method of scoring the pain drawing and demonstrate psychometric generalizability among patients with cancerrelated pain. Using the Wilcoxon signed rank test and associated effect sizes, results show significant improvement in dispersion of pain following SNN. Effect sizes for the difference in pre-SNN to 2 post-SNN time points were higher for the pain drawing than for pain intensity rating. Specifically, the effect size difference from pre- to within one month post-SNN was r = 0.42 for pain drawing versus r = 0.23 for pain intensity rating. Based on a smaller subset of patients who were seen within 1 – 6 months following SNN, the effect size difference from pre-SNN was r = 0.46 for pain drawing versus r = 0.00 for pain intensity rating. Collectively, these data support the use of the pain drawing as a reliable outcome measure among patients with cancer pain for procedures such as SNN that target specific location and dispersion of pain. Key words: Cancer pain, pain drawing, splanchnic block

APA, Harvard, Vancouver, ISO, and other styles

2

Al-Hamid, Ali A., and HyungWon Kim. "Optimization of Spiking Neural Networks Based on Binary Streamed Rate Coding." Electronics 9, no. 10 (September 29, 2020): 1599. http://dx.doi.org/10.3390/electronics9101599.

Full text

Abstract:

Spiking neural networks (SNN) increasingly attract attention for their similarity to the biological neural system. Hardware implementation of spiking neural networks, however, remains a great challenge due to their excessive complexity and circuit size. This work introduces a novel optimization method for hardware friendly SNN architecture based on a modified rate coding scheme called Binary Streamed Rate Coding (BSRC). BSRC combines the features of both rate and temporal coding. In addition, by employing a built-in randomizer, the BSRC SNN model provides a higher accuracy and faster training. We also present SNN optimization methods including structure optimization and weight quantization. Extensive evaluations with MNIST SNNs demonstrate that the structure optimization of SNN (81-30-20-10) provides 183.19 times reduction in hardware compared with SNN (784-800-10), while providing an accuracy of 95.25%, a small loss compared with 98.89% and 98.93% reported in the previous works. Our weight quantization reduces 32-bit weights to 4-bit integers leading to further hardware reduction of 4 times with only 0.56% accuracy loss. Overall, the SNN model (81-30-20-10) optimized by our method shrinks the SNN’s circuit area from 3089.49 mm2 for SNN (784-800-10) to 4.04 mm2—a reduction of 765 times.

APA, Harvard, Vancouver, ISO, and other styles

3

Neiva, Flávia Cristina Brisque, and Cléa Rodrigues Leone. "Sucção em recém-nascidos pré-termo e estimulação da sucção." Pró-Fono Revista de Atualização Científica 18, no. 2 (August 2006): 141–50. http://dx.doi.org/10.1590/s0104-56872006000200003.

Full text

Abstract:

TEMA: a estimulação da sucção não-nutritiva pode antecipar o início da alimentação por via oral e influenciar a evolução da sucção em recém-nascidos pré-termo. OBJETIVO: descrever a evolução do padrão de sucção e os efeitos da estimulação da sucção não-nutritiva (SNN). MÉTODO: foram estudados 95 recém-nascidos pré-termo (RNPT) adequados para a idade gestacional (IG), com IG ao nascer menor ou igual a 33 semanas, distribuídos de forma aleatória em três grupos: Grupo 1 (G1), grupo controle, sem estimulação da SNN; Grupo 2 (G2), com estimulação da SNN com chupeta ortodôntica para prematuros NUK® e Grupo 3 (G3), com estimulação da SNN através do dedo enluvado. Os três grupos foram submetidos a avaliação semanal da SNN com dedo enluvado e, após o início da alimentação por via oral (VO), avaliação da SNN e da sucção nutritiva (SN) com mini-mamadeira. RESULTADOS: nos três grupos, com o aumento da IG corrigida, elevou-se a probabilidade de ocorrência de todas as características da sucção estudadas (SNN e SN), exceto sinais de estresse na SNN e coordenação sucção-deglutição-respiração na SN. Na SNN: sucção iniciada facilmente (SIF), ritmo, força e coordenação lábios, língua e mandíbula, sem diferenças entre os grupos; probabilidade maior de vedamento labial, acanolamento, peristaltismo no G3 e de sinais de estresse no G2 (> 37 semanas). Na sucção nutritiva (SN): SIF, coordenação movimentos de lábios-língua e mandíbula, volume de leite ingerido pelo tempo total sem diferenças entre os grupos; ritmo e coordenação sucção-deglutição-respiração superior no G3; vedamento labial superior nos G1 e 3 (< 34 semanas) e sinais de estresse superior no G2 (> 33 semanas). CONCLUSÃO: o padrão de sucção de RNPT evoluiu em função da IG corrigida, tendo a estimulação da SNN aumentado a probabilidade de ocorrência de vedamento labial, ritmo, acanolamento, peristaltismo e coordenação sucção-deglutição-respiração, sendo o dedo enluvado a forma mais eficaz de estimulação da SNN.

APA, Harvard, Vancouver, ISO, and other styles

4

Galán-Prado, Fabio, Alejandro Morán, Joan Font, Miquel Roca, and Josep L. Rosselló. "Compact Hardware Synthesis of Stochastic Spiking Neural Networks." International Journal of Neural Systems 29, no. 08 (September 25, 2019): 1950004. http://dx.doi.org/10.1142/s0129065719500047.

Full text

Abstract:

Spiking neural networks (SNN) are able to emulate real neural behavior with high confidence due to their bio-inspired nature. Many designs have been proposed for the implementation of SNN in hardware, although the realization of high-density and biologically-inspired SNN is currently a complex challenge of high scientific and technical interest. In this work, we propose a compact digital design for the implementation of high-volume SNN that considers the intrinsic stochastic processes present in biological neurons and enables high-density hardware implementation. The proposed stochastic SNN model (SSNN) is compared with previous SSNN models, achieving a higher processing speed. We also show how the proposed model can be scaled to high-volume neural networks trained by using back propagation and applied to a pattern classification task. The proposed model achieves better results compared with other recently-published SNN models configured with unsupervised STDP learning.

APA, Harvard, Vancouver, ISO, and other styles

5

Ma, Zansong, Xiangbing Shu, Jie Huang, Haiyan Zhang, Zhen Xiao, and Li Zhang. "Salvia-Nelumbinis Naturalis Formula Improved Inflammation in LPS Stressed Macrophages via Upregulating MicroRNA-152." Mediators of Inflammation 2017 (2017): 1–9. http://dx.doi.org/10.1155/2017/5842747.

Full text

Abstract:

Salvia-Nelumbinis naturalis (SNN) formula is an effective agent in treating nonalcoholic steatohepatitis (NASH); however, the precise mechanisms are still undefined. Activation of Kupffer cells by gut-derived lipopolysaccharide (LPS) plays a central role in the pathogenesis of NASH. In the present study, we aimed to explore the epigenetic regulation of microRNAs under the beneficial effects of SNN-containing serum in LPS stressed macrophages. Kupffer cells were isolated from C57BL/6 mice and treated with LPS or LPS and SNN-containing serum; the mRNA expression of tumor necrosis factor-α (TNF-α) and interleukin-6 (IL-6) was assessed. By using microarray chips, we investigated differentially expressed microRNA profiles to decipher the underlining mechanisms of SNN-containing serum. It was revealed that SNN-containing serum decreased TNF-α and IL-6 expression, and microRNA-152 was identified as the potential epigenetic regulator. We further verified the pharmacological effects in Raw264.7 cells; while transfection with miRNA-152 mimics could reduce TNF-α and IL-6, transfection with miRNA-152 inhibitor blocked the anti-inflammatory effect of SNN-containing serum. These results suggested that SNN-containing serum could improve inflammation in LPS stressed Kupffer cells and macrophages via upregulating microRNA-152.

APA, Harvard, Vancouver, ISO, and other styles

6

NICHOLS, ERIC, L. J. McDAID, and N. H. SIDDIQUE. "CASE STUDY ON A SELF-ORGANIZING SPIKING NEURAL NETWORK FOR ROBOT NAVIGATION." International Journal of Neural Systems 20, no. 06 (December 2010): 501–8. http://dx.doi.org/10.1142/s0129065710002577.

Full text

Abstract:

This paper presents a Spiking Neural Network (SNN) architecture for mobile robot navigation. The SNN contains 4 layers where dynamic synapses route information to the appropriate neurons in each layer and the neurons are modeled using the Leaky Integrate and Fire (LIF) model. The SNN learns by self-organizing its connectivity as new environmental conditions are experienced and consequently knowledge about its environment is stored in the connectivity. Also a novel feature of the proposed SNN architecture is that it uses working memory, where present and previous sensor states are stored. Results are presented for a wall following application.

APA, Harvard, Vancouver, ISO, and other styles

7

Aoun, Mario Antoine. "A STDP Rule that Favours Chaotic Spiking over Regular Spiking of Neurons." International Journal of Artificial Intelligence & Applications 12, no. 03 (May 31, 2021): 25–33. http://dx.doi.org/10.5121/ijaia.2021.12303.

Full text

Abstract:

We compare the number of states of a Spiking Neural Network (SNN) composed from chaotic spiking neurons versus the number of states of a SNN composed from regular spiking neurons while both SNNs implementing a Spike Timing Dependent Plasticity (STDP) rule that we created. We find out that this STDP rule favors chaotic spiking since the number of states is larger in the chaotic SNN than the regular SNN. This chaotic favorability is not general; it is exclusive to this STDP rule only. This research falls under our long-term investigation of STDP and chaos theory.

APA, Harvard, Vancouver, ISO, and other styles

8

Shang, Ying, Yongli Li, Feng You, and RuiLian Zhao. "Conversion-based Approach to Obtain an SNN Construction." International Journal of Software Engineering and Knowledge Engineering 30, no. 11n12 (November 2020): 1801–18. http://dx.doi.org/10.1142/s0218194020400318.

Full text

Abstract:

Spiking Neuron Network (SNN) uses spike sequence for data processing, so it has an excellent characteristic of low power consumption. However, due to the immaturity of learning algorithm, the multiplayer network training has difficulty in convergence. Utilizing the mature learning algorithm and fast training speed of the back-propagation network, this paper proposes a method to converse the Convolutional Neural Network (CNN) to the SNN. First, the adjustment strategy for CNN is introduced. Then after training, the weight parameters in the model are extracted, which is the corresponding synaptic weight in the layer of the SNN. Finally, a new threshold-setting algorithm based on feedback is proposed to solve the critical problem of the threshold setting of neurons in the SNN. We evaluate our method on the CIFAR-10 datasets released by Hinton’s team. The experimental results show that the image classification accuracy of the SNN is more than 98% of that of CNN, and the theoretical value of power consumption per second is 3.9[Formula: see text]mW.

APA, Harvard, Vancouver, ISO, and other styles

9

Lu, L., X. Wei, Y. H. Li, and W. B. Li. "Sentinel node necrosis is a negative prognostic factor in patients with nasopharyngeal carcinoma: a magnetic resonance imaging study of 252 patients." Current Oncology 24, no. 3 (June 28, 2017): 220. http://dx.doi.org/10.3747/co.24.3168.

Full text

Abstract:

Purpose We explored the patterns of sentinel node metastasis and investigated the prognostic value of sentinel node necrosis (snn) in patients with nasopharyngeal carcinoma (npc), based on magnetic resonance imaging (mri).Methods This retrospective study enrolled 252 patients at our institution who had metastatic lymph nodes from biopsy-confirmed npc and who were treated with definitive radiation therapy, with or without chemotherapy. All participants underwent mri before treatment, and the resulting images were reviewed to evaluate lymph node status. The patients were divided into snn and non-snn groups. Overall survival (os), tumour-free survival (tfs), regional relapse–free survival (rrfs), and distant metastasis–free survival (dmfs) were calculated by the Kaplan–Meier method, and differences were compared using the log-rank test. Factors predictive of outcome were determined by univariate and multivariate analysis.Results Of the 252 patients, 189 (75%) had retropharyngeal lymph node metastasis, and 189 (75%) had level iia or iib lymph node necrosis. The incidence of snn was 43.4% (91 of 210 patients with lymph node metastasis or necrosis, or both). After a median follow-up of 54 months, the 5-year rates of os, tfs, rrfs, and dmfs in the snn and non-snn groups were, respectively, 79.4% and 95.3%, 73.5% and 93.3%, 80.4% and 96.6%, and 75.5% and 95.3% (all p < 0.01). Age greater than 40 years, snn, T stage, and N stage were significant independent negative prognostic factors for os, tfs, rrfs, and dmfs.Conclusions Metastatic retropharyngeal lymph nodes and necrotic level ii nodes both seem to act as sentinels. Sentinel node necrosis is an negative prognostic factor in patients with npc. Patients with snn have a worse prognosis.

APA, Harvard, Vancouver, ISO, and other styles

10

Chiu, Chih-Chin, Chen-Ya Yang, Tsui-Fen Yang, Kon-Ping Lin, Shou-Hsien Huang, and Jia-Chi Wang. "Acute Sensory Neuronopathy following Enterovirus Infection in a 3-Year-Old Girl." Neuropediatrics 48, no. 03 (March 23, 2017): 190–93. http://dx.doi.org/10.1055/s-0037-1601323.

Full text

Abstract:

AbstractAcute sensory neuronopathy (SNN) is a rapidly developing peripheral nervous system disease that primarily affects sensory neurons in the dorsal root ganglion or trigeminal ganglion, leading to the impairment of sensory axons. SNN is notably uncommon in childhood; only three cases of childhood or adolescent SNN have been reported to date. Moreover, SSN has never been reported in association with enterovirus infection. Here, we report the case of a 3-year-old girl who was initially diagnosed with enterovirus infection based on the presentation of fevers, rashes on all extremities, and ulceration over the posterior pharynx. Nine days later, she presented with ataxic and wide-based gait and dysmetria affecting the extremities, with an absence of sensory nerve action potentials in the upper and lower limbs. The patient was diagnosed with acute SNN based on the criteria developed by Camdessanché et al in 2009. To our knowledge, this is the youngest case of SNN reported to date. In addition, this case reveals that enterovirus infection can be associated with acute SNN in children in rare cases. Accurate diagnosis relies on clinical suspicion, comprehensive knowledge of the patient's history, and careful characterization of abnormal findings in electrodiagnostic studies.

APA, Harvard, Vancouver, ISO, and other styles

11

Lobov, Sergey A., Alexey I. Zharinov, Valeri A. Makarov, and Victor B. Kazantsev. "Spatial Memory in a Spiking Neural Network with Robot Embodiment." Sensors 21, no. 8 (April 10, 2021): 2678. http://dx.doi.org/10.3390/s21082678.

Full text

Abstract:

Cognitive maps and spatial memory are fundamental paradigms of brain functioning. Here, we present a spiking neural network (SNN) capable of generating an internal representation of the external environment and implementing spatial memory. The SNN initially has a non-specific architecture, which is then shaped by Hebbian-type synaptic plasticity. The network receives stimuli at specific loci, while the memory retrieval operates as a functional SNN response in the form of population bursts. The SNN function is explored through its embodiment in a robot moving in an arena with safe and dangerous zones. We propose a measure of the global network memory using the synaptic vector field approach to validate results and calculate information characteristics, including learning curves. We show that after training, the SNN can effectively control the robot’s cognitive behavior, allowing it to avoid dangerous regions in the arena. However, the learning is not perfect. The robot eventually visits dangerous areas. Such behavior, also observed in animals, enables relearning in time-evolving environments. If a dangerous zone moves into another place, the SNN remaps positive and negative areas, allowing escaping the catastrophic interference phenomenon known for some AI architectures. Thus, the robot adapts to changing world.

APA, Harvard, Vancouver, ISO, and other styles

12

Hwang, Sungmin, Jeong-Jun Lee, Min-Woo Kwon, Myung-Hyun Baek, Taejin Jang, Jeesoo Chang, Jong-Ho Lee, and Byung-Gook Park. "Analog Complementary Metal–Oxide–Semiconductor Integrate-and-Fire Neuron Circuit for Overflow Retaining in Hardware Spiking Neural Networks." Journal of Nanoscience and Nanotechnology 20, no. 5 (May 1, 2020): 3117–22. http://dx.doi.org/10.1166/jnn.2020.17390.

Full text

Abstract:

The spiking neural network (SNN) is regarded as the third generation of an artificial neural network (ANN). In order to realize a high-performance SNN, an integrate-and-fire (I&F) neuron, one of the key elements in an SNN, must retain the overflow in its membrane after firing. This paper presents an analog CMOS I&F neuron circuit for overflow retaining. Compared with the conventional I&F neuron circuit, the basic operation of the proposed circuit is confirmed in a circuit-level simulation. Furthermore, a single-layer SNN simulation was also performed to demonstrate the effect of the proposed circuit on neural network applications by comparing the raster plots from the circuit-level simulation with those from a high-level simulation. These results demonstrate the potential of the I&F neuron circuit with overflow retaining characteristics to be utilized in upcoming high-performance hardware SNN systems.

APA, Harvard, Vancouver, ISO, and other styles

13

Nichols, Eric, Liam J. McDaid, and Nazmul Siddique. "Biologically Inspired SNN for Robot Control." IEEE Transactions on Cybernetics 43, no. 1 (February 2013): 115–28. http://dx.doi.org/10.1109/tsmcb.2012.2200674.

Full text

APA, Harvard, Vancouver, ISO, and other styles

14

Hulea, Mircea, George Iulian Uleru, and Constantin Florin Caruntu. "Adaptive SNN for Anthropomorphic Finger Control." Sensors 21, no. 8 (April 13, 2021): 2730. http://dx.doi.org/10.3390/s21082730.

Full text

Abstract:

Anthropomorphic hands that mimic the smoothness of human hand motions should be controlled by artificial units of high biological plausibility. Adaptability is among the characteristics of such control units, which provides the anthropomorphic hand with the ability to learn motions. This paper presents a simple structure of an adaptive spiking neural network implemented in analogue hardware that can be trained using Hebbian learning mechanisms to rotate the metacarpophalangeal joint of a robotic finger towards targeted angle intervals. Being bioinspired, the spiking neural network drives actuators made of shape memory alloy and receives feedback from neuromorphic sensors that convert the joint rotation angle and compression force into the spiking frequency. The adaptive SNN activates independent neural paths that correspond to angle intervals and learns in which of these intervals the rotation the finger rotation is stopped by an external force. Learning occurs when angle-specific neural paths are stimulated concurrently with the supraliminar stimulus that activates all the neurons that inhibit the SNN output stopping the finger. The results showed that after learning, the finger stopped in the angle interval in which the angle-specific neural path was active, without the activation of the supraliminar stimulus. The proposed concept can be used to implement control units for anthropomorphic robots that are able to learn motions unsupervised, based on principles of high biological plausibility.

APA, Harvard, Vancouver, ISO, and other styles

15

Madenda, Sarifuddin, and Suryadi Harmanto. "NEW APPROACH OF SIGNED BINARY NUMBERS MULTIPLICATION AND ITS IMPLEMENTATION ON FPGA." Jurnal Ilmiah Teknologi dan Rekayasa 26, no. 1 (2021): 56–68. http://dx.doi.org/10.35760/tr.2021.v26i1.3703.

Full text

Abstract:

This paper proposes a new model of signed binary multiplication. This model is formulated mathematically and can handle four types of binary multipliers: signed positive numbers multiplied by signed positive numbers (SPN-by-SPN); signed positive numbers multiplied by signed negative numbers (SPN-by-SNN); signed negative numbers multiplied by signed positive numbers (SNN-by-SPN); and signed negative numbers multiplied by signed negative numbers (SNN-by-SNN). The proposed model has a low complexity algorithm, is easy to implement in software coding and integrated in a hardware FPGA (Field-Programmable Gate Array), and is more powerful compared to the modified Baugh-Wooley's model.

APA, Harvard, Vancouver, ISO, and other styles

16

Wu, Yang. "Recent results for STAR sNN=4.9GeV Al+Au and sNN=4.5GeV Au+Au Fixed-Target Collisions." Nuclear Physics A 982 (February 2019): 899–902. http://dx.doi.org/10.1016/j.nuclphysa.2018.10.051.

Full text

APA, Harvard, Vancouver, ISO, and other styles

17

Ali, Aziz Nasser Boraik, Hassan Pyar Ali Hassan, and Hesham Bahamish. "SNN-SB: Combining Partial Alignment Using Modified SNN Algorithm with Segment-Based for Multiple Sequence Alignments." Journal of Physics: Conference Series 1962, no. 1 (July 1, 2021): 012048. http://dx.doi.org/10.1088/1742-6596/1962/1/012048.

Full text

APA, Harvard, Vancouver, ISO, and other styles

18

Li, Ming, Haibo Ruan, Yu Qi, Tiantian Guo, Ping Wang, and Gang Pan. "Odor Recognition with a Spiking Neural Network for Bioelectronic Nose." Sensors 19, no. 5 (February 26, 2019): 993. http://dx.doi.org/10.3390/s19050993.

Full text

Abstract:

Electronic noses recognize odors using sensor arrays, and usually face difficulties for odor complicacy, while animals have their own biological sensory capabilities for various types of odors. By implanting electrodes into the olfactory bulb of mammalian animals, odors may be recognized by decoding the recorded neural signals, in order to construct a bioelectronic nose. This paper proposes a spiking neural network (SNN)-based odor recognition method from spike trains recorded by the implanted electrode array. The proposed SNN-based approach exploits rich timing information well in precise time points of spikes. To alleviate the overfitting problem, we design a new SNN learning method with a voltage-based regulation strategy. Experiments are carried out using spike train signals recorded from the main olfactory bulb in rats. Results show that our SNN-based approach achieves the state-of-the-art performance, compared with other methods. With the proposed voltage regulation strategy, it achieves about 15% improvement compared with a classical SNN model.

APA, Harvard, Vancouver, ISO, and other styles

19

ZAVALIAGKOS, G., S. AUSTIN, J. MAKHOUL, and R. SCHWARTZ. "A HYBRID CONTINUOUS SPEECH RECOGNITION SYSTEM USING SEGMENTAL NEURAL NETS WITH HIDDEN MARKOV MODELS." International Journal of Pattern Recognition and Artificial Intelligence 07, no. 04 (August 1993): 949–63. http://dx.doi.org/10.1142/s0218001493000480.

Full text

Abstract:

Up till recently, state-of-the-art, large vocabulary, continuous speech recognition (CSR) had employed hidden Markov modeling (HMM) to model speech sounds. In an attempt to improve over HMM we developed a hybrid system that integrates HMM technology with neural networks. We present the concept of a Segmental Neural Net (SNN) for phonetic modeling in CSR. By taking into account all the frames of a phonetic segment simultaneously, the SNN overcomes the well-known conditional-independence limitation of HMMs. We have developed a novel hybrid SNN/HMM system that combines the advantages of SNNs and HMMs using a multiple hypothesis (or N-best) paradigm. In this system, we generate likely phonetic segmentations from the HMM N-best list of word sequences, which are scored by the SNN. The HMM and SNN scores are then combined to optimize performance. In several speaker-independent, 1000-word CSR tests, the error rate for the hybrid system dropped 20% from that of a state-of-the-art HMM system alone.

APA, Harvard, Vancouver, ISO, and other styles

20

Pang, Lili, Junxiu Liu, Jim Harkin, George Martin, Malachy McElholm, Aqib Javed, and Liam McDaid. "Case Study—Spiking Neural Network Hardware System for Structural Health Monitoring." Sensors 20, no. 18 (September 8, 2020): 5126. http://dx.doi.org/10.3390/s20185126.

Full text

Abstract:

This case study provides feasibility analysis of adapting Spiking Neural Networks (SNN) based Structural Health Monitoring (SHM) system to explore low-cost solution for inspection of structural health of damaged buildings which survived after natural disaster that is, earthquakes or similar activities. Various techniques are used to detect the structural health status of a building for performance benchmarking, including different feature extraction methods and classification techniques (e.g., SNN, K-means and artificial neural network etc.). The SNN is utilized to process the sensory data generated from full-scale seven-story reinforced concrete building to verify the classification performances. Results show that the proposed SNN hardware has high classification accuracy, reliability, longevity and low hardware area overhead.

APA, Harvard, Vancouver, ISO, and other styles

21

Tan, JingDong, and RuJing Wang. "Smooth Splicing: A Robust SNN-Based Method for Clustering High-Dimensional Data." Mathematical Problems in Engineering 2013 (2013): 1–9. http://dx.doi.org/10.1155/2013/295067.

Full text

Abstract:

Sharing nearest neighbor (SNN) is a novel metric measure of similarity, and it can conquer two hardships: the low similarities between samples and the different densities of classes. At present, there are two popular SNN similarity based clustering methods: JP clustering and SNN density based clustering. Their clustering results highly rely on the weighting value of the single edge, and thus they are very vulnerable. Motivated by the idea of smooth splicing in computing geometry, the authors design a novel SNN similarity based clustering algorithm within the structure of graph theory. Since it inherits complementary intensity-smoothness principle, its generalizing ability surpasses those of the previously mentioned two methods. The experiments on text datasets show its effectiveness.

APA, Harvard, Vancouver, ISO, and other styles

22

Mo, Lingfei, and Minghao Wang. "LogicSNN: A Unified Spiking Neural Networks Logical Operation Paradigm." Electronics 10, no. 17 (August 31, 2021): 2123. http://dx.doi.org/10.3390/electronics10172123.

Full text

Abstract:

LogicSNN, a unified spiking neural networks (SNN) logical operation paradigm is proposed in this paper. First, we define the logical variables under the semantics of SNN. Then, we design the network structure of this paradigm and use spike-timing-dependent plasticity for training. According to this paradigm, six kinds of basic SNN binary logical operation modules and three kinds of combined logical networks based on these basic modules are implemented. Through these experiments, the rationality, cascading characteristics and the potential of building large-scale network of this paradigm are verified. This study fills in the blanks of the logical operation of SNN and provides a possible way to realize more complex machine learning capabilities.

APA, Harvard, Vancouver, ISO, and other styles

23

Asghar, Malik Summair, Saad Arslan, and Hyungwon Kim. "A Low-Power Spiking Neural Network Chip Based on a Compact LIF Neuron and Binary Exponential Charge Injector Synapse Circuits." Sensors 21, no. 13 (June 29, 2021): 4462. http://dx.doi.org/10.3390/s21134462.

Full text

Abstract:

To realize a large-scale Spiking Neural Network (SNN) on hardware for mobile applications, area and power optimized electronic circuit design is critical. In this work, an area and power optimized hardware implementation of a large-scale SNN for real time IoT applications is presented. The analog Complementary Metal Oxide Semiconductor (CMOS) implementation incorporates neuron and synaptic circuits optimized for area and power consumption. The asynchronous neuronal circuits implemented benefit from higher energy efficiency and higher sensitivity. The proposed synapse circuit based on Binary Exponential Charge Injector (BECI) saves area and power consumption, and provides design scalability for higher resolutions. The SNN model implemented is optimized for 9 × 9 pixel input image and minimum bit-width weights that can satisfy target accuracy, occupies less area and power consumption. Moreover, the spiking neural network is replicated in full digital implementation for area and power comparisons. The SNN chip integrated from neuron and synapse circuits is capable of pattern recognition. The proposed SNN chip is fabricated using 180 nm CMOS process, which occupies a 3.6 mm2 chip core area, and achieves a classification accuracy of 94.66% for the MNIST dataset. The proposed SNN chip consumes an average power of 1.06 mW—20 times lower than the digital implementation.

APA, Harvard, Vancouver, ISO, and other styles

24

Das, Debasish. "HBT Radii: Comparative Studies on Collision Systems and Beam Energies." Advances in High Energy Physics 2018 (July 15, 2018): 1–5. http://dx.doi.org/10.1155/2018/3794242.

Full text

Abstract:

Two-particle Hanbury-Brown-Twiss (HBT) interferometry is an important probe for understanding the space-time structure of particle emission sources in high energy heavy ion collisions. We present the comparative studies of HBT radii in Pb+Pb collisions at sNN = 17.3 GeV with Au+Au collisions at sNN = 19.6 GeV. To further understand this specific energy regime, we also compare the HBT radii for Au+Au collisions at sNN = 19.6 GeV with Cu+Cu collisions at sNN = 22.4 GeV. We have found interesting similarity in the Rout/Rside ratio with mT across the collision systems while comparing the data for this specific energy zone which is interesting as it acts as a bridge from SPS energy regime to the RHIC energy domain.

APA, Harvard, Vancouver, ISO, and other styles

25

Zhu, Xi, Yi Sun, Haijun Liu, Qingjiang Li, and Hui Xu. "Simulation of the Spiking Neural Network based on Practical Memristor." MATEC Web of Conferences 173 (2018): 01025. http://dx.doi.org/10.1051/matecconf/201817301025.

Full text

Abstract:

In order to gain a better understanding of the brain and explore biologically-inspired computation, significant attention is being paid to research into the spike-based neural computation. Spiking neural network (SNN), which is inspired by the understanding of observed biological structure, has been increasingly applied to pattern recognition task. In this work, a single layer SNN architecture based on the characteristics of spiking timing dependent plasticity (STDP) in accordance with the actual test of the device data has been proposed. The device data is derived from the Ag/GeSe/TiN fabricated memristor. The network has been tested on the MNIST dataset, and the classification accuracy attains 90.2%. Furthermore, the impact of device instability on the SNN performance has been discussed, which can propose guidelines for fabricating memristors used for SNN architecture based on STDP characteristics.

APA, Harvard, Vancouver, ISO, and other styles

26

Lim, Kian Hwee, Aik Hui Chan, and Choo Hiap Oh. "Transverse Energy Density in High Energy Heavy Ion Collisions." EPJ Web of Conferences 240 (2020): 07006. http://dx.doi.org/10.1051/epjconf/202024007006.

Full text

Abstract:

A phenomenological model describing the transverse energy distribution (ET) of nuclear collisions is ﬁrst studied in detail by ﬁtting it on ET data for O-Pb collisions at √sNN = 200 GeV per nucleon obtained from the NA35 collaboration. Next, the model is used to ﬁt the ET data for Pb-Pb collisions at LHC energies of √sNN = 2.76 TeV per nucleon obtained from the ATLAS collaboration. From the ﬁts, we determine an upper bound for the energy density for Pb-Pb collisions at LHC energies of √sNN = 2.76 TeV per nucleon.

APA, Harvard, Vancouver, ISO, and other styles

27

Ackermann, K. H., N. Adams, C. Adler, Z. Ahammed, S. Ahmad, C. Allgower, J. Amsbaugh, et al. "Elliptic Flow inAu+AuCollisions at√sNN=130GeV." Physical Review Letters 86, no. 3 (January 15, 2001): 402–7. http://dx.doi.org/10.1103/physrevlett.86.402.

Full text

APA, Harvard, Vancouver, ISO, and other styles

28

Su, Jing, and Jing Li. "HF-SNN: High-Frequency Spiking Neural Network." IEEE Access 9 (2021): 51950–57. http://dx.doi.org/10.1109/access.2021.3068159.

Full text

APA, Harvard, Vancouver, ISO, and other styles

29

Shu, Xiangbing, Miao Wang, Hanchen Xu, Yang Liu, Jie Huang, Zemin Yao, and Li Zhang. "Extracts of Salvia-Nelumbinis Naturalis Ameliorate Nonalcoholic Steatohepatitis via Inhibiting Gut-Derived Endotoxin Mediated TLR4/NF-κB Activation." Evidence-Based Complementary and Alternative Medicine 2017 (2017): 1–13. http://dx.doi.org/10.1155/2017/9208314.

Full text

Abstract:

Nonalcoholic steatohepatitis (NASH) is featured by the presence of hepatic steatosis combined with inflammation and hepatocellular injury. Gut-derived endotoxin plays a crucial role in the pathogenesis of NASH. Salvia-Nelumbinis naturalis (SNN), a formula of Traditional Chinese Medicine, has been identified to be effective for NASH, but the mechanisms were not thoroughly explored. In the present study, a NASH model was generated using C57BL/6 mice fed a high fat diet (HFD) supplemented periodically with dextran sulfate sodium (DSS) in drinking water for 12 weeks. Mice fed HFD alone (without DSS) or chow diet were used as controls. The NASH mice were given the SNN extracts in the following 4 weeks, while control mice were provided with saline. Mice fed HFD developed steatosis, and DSS supplementation resulted in NASH. The SNN extracts significantly improved metabolic disorders including obesity, dyslipidemia, and liver steatosis and reduced hepatic inflammation, circulating tumor necrosis factor-α (TNF-α), and lipopolysaccharide (LPS) levels. The beneficial effect of the SNN extracts was associated with restoration of intestinal conditions (microbiota, integrity of intestinal barrier) and inhibition of TLR4/NF-κB activation. These results suggest that the SNN extracts ameliorate NASH progression, possibly through blocking endotoxin related TLR4/NF-κB activation.

APA, Harvard, Vancouver, ISO, and other styles

30

He, Qiurui, Zhenzhan Wang, and Jiaoyang Li. "Application of the Deep Neural Network in Retrieving the Atmospheric Temperature and Humidity Profiles from the Microwave Humidity and Temperature Sounder Onboard the Feng-Yun-3 Satellite." Sensors 21, no. 14 (July 8, 2021): 4673. http://dx.doi.org/10.3390/s21144673.

Full text

Abstract:

The shallow neural network (SNN) is a popular algorithm in atmospheric parameters retrieval from microwave remote sensing. However, the deep neural network (DNN) has a stronger nonlinear mapping capability compared to SNN and has great potential for applications in microwave remote sensing. The Microwave Humidity and Temperature Sounder (Beijing, China, MWHTS) onboard the Fengyun-3 (FY-3) satellite has the ability to independently retrieve atmospheric temperature and humidity profiles. A study on the application of DNN in retrieving atmospheric temperature and humidity profiles from MWHTS was carried out. Three retrieval schemes of atmospheric parameters in microwave remote sensing based on DNN were performed in the study of bias correction of MWHTS observation and the retrieval of the atmospheric temperature and humidity profiles using MWHTS observations. The experimental results show that, compared with SNN, DNN can obtain better bias-correction results when applied to MWHTS observation, and can obtain higher retrieval accuracy of temperature and humidity profiles in all three retrieval schemes. Meanwhile, DNN shows higher stability than SNN when applied to the retrieval of temperature and humidity profiles. The comparative study of DNN and SNN applied in different atmospheric parameter retrieval schemes shows that DNN has a more superior performance.

APA, Harvard, Vancouver, ISO, and other styles

31

Hwang, Sungmin, Hyungjin Kim, and Byung-Gook Park. "Quantized Weight Transfer Method Using Spike-Timing-Dependent Plasticity for Hardware Spiking Neural Network." Applied Sciences 11, no. 5 (February 25, 2021): 2059. http://dx.doi.org/10.3390/app11052059.

Full text

Abstract:

A hardware-based spiking neural network (SNN) has attracted many researcher’s attention due to its energy-efficiency. When implementing the hardware-based SNN, offline training is most commonly used by which trained weights by a software-based artificial neural network (ANN) are transferred to synaptic devices. However, it is time-consuming to map all the synaptic weights as the scale of the neural network increases. In this paper, we propose a method for quantized weight transfer using spike-timing-dependent plasticity (STDP) for hardware-based SNN. STDP is an online learning algorithm for SNN, but we utilize it as the weight transfer method. Firstly, we train SNN using the Modified National Institute of Standards and Technology (MNIST) dataset and perform weight quantization. Next, the quantized weights are mapped to the synaptic devices using STDP, by which all the synaptic weights connected to a neuron are transferred simultaneously, reducing the number of pulse steps. The performance of the proposed method is confirmed, and it is demonstrated that there is little reduction in the accuracy at more than a certain level of quantization, but the number of pulse steps for weight transfer substantially decreased. In addition, the effect of the device variation is verified.

APA, Harvard, Vancouver, ISO, and other styles

32

Wu, Di, Qiuying Du, Xue Wu, Ruili Shi, Linwei Sai, Xiaoqing Liang, Xiaoming Huang, and Jijun Zhao. "Evolution of atomic structures of SnN, SnN−, and SnNCl− clusters (N = 4–20): Insight from ab initio calculations." Journal of Chemical Physics 150, no. 17 (May 7, 2019): 174304. http://dx.doi.org/10.1063/1.5095437.

Full text

APA, Harvard, Vancouver, ISO, and other styles

33

Lobov, Sergey A., Andrey V. Chernyshov, Nadia P. Krilova, Maxim O. Shamshin, and Victor B. Kazantsev. "Competitive Learning in a Spiking Neural Network: Towards an Intelligent Pattern Classifier." Sensors 20, no. 2 (January 16, 2020): 500. http://dx.doi.org/10.3390/s20020500.

Full text

Abstract:

One of the modern trends in the design of human–machine interfaces (HMI) is to involve the so called spiking neuron networks (SNNs) in signal processing. The SNNs can be trained by simple and efficient biologically inspired algorithms. In particular, we have shown that sensory neurons in the input layer of SNNs can simultaneously encode the input signal based both on the spiking frequency rate and on varying the latency in generating spikes. In the case of such mixed temporal-rate coding, the SNN should implement learning working properly for both types of coding. Based on this, we investigate how a single neuron can be trained with pure rate and temporal patterns, and then build a universal SNN that is trained using mixed coding. In particular, we study Hebbian and competitive learning in SNN in the context of temporal and rate coding problems. We show that the use of Hebbian learning through pair-based and triplet-based spike timing-dependent plasticity (STDP) rule is accomplishable for temporal coding, but not for rate coding. Synaptic competition inducing depression of poorly used synapses is required to ensure a neural selectivity in the rate coding. This kind of competition can be implemented by the so-called forgetting function that is dependent on neuron activity. We show that coherent use of the triplet-based STDP and synaptic competition with the forgetting function is sufficient for the rate coding. Next, we propose a SNN capable of classifying electromyographical (EMG) patterns using an unsupervised learning procedure. The neuron competition achieved via lateral inhibition ensures the “winner takes all” principle among classifier neurons. The SNN also provides gradual output response dependent on muscular contraction strength. Furthermore, we modify the SNN to implement a supervised learning method based on stimulation of the target classifier neuron synchronously with the network input. In a problem of discrimination of three EMG patterns, the SNN with supervised learning shows median accuracy 99.5% that is close to the result demonstrated by multi-layer perceptron learned by back propagation of an error algorithm.

APA, Harvard, Vancouver, ISO, and other styles

34

Neiva, Flávia Cristina B., and Cléa Rodrigues Leone. "Efeitos da estimulação da sucção não-nutritiva na idade de início da alimentação via oral em recém-nascidos pré-termo." Revista Paulista de Pediatria 25, no. 2 (June 2007): 129–34. http://dx.doi.org/10.1590/s0103-05822007000200006.

Full text

Abstract:

OBJETIVO: Analisar os efeitos da estimulação da sucção não-nutritiva (SNN) sobre a idade de início da alimentação via oral (VO) em recém-nascidos pré-termo (RNPT). MÉTODOS: Foram estudados 95 RNPT, com idade gestacional (IG) de nascimento <33 semanas, nascidos no Berçário Anexo à Maternidade do Hospital das Clínicas, Serviço de Pediatria Clínica, Intensiva e Neonatal do Instituto da Criança da Faculdade de Medicina da Universidade de São Paulo (FMUSP). Estes foram distribuídos em três grupos: Grupo 1, grupo controle, sem estimulação; Grupo 2, estimulação da SNN com chupeta ortodôntica Nuk® para prematuros; e Grupo 3, estimulação da SNN com dedo enluvado. RESULTADOS: Os RN tinham IG ao nascer de 26 a 32,7 semanas (30,5±1,6), IG corrigida ao entrar no estudo de 27,4 a 33 semanas (31,6±1,3) e peso de nascimento médio de 1.390g, sem diferenças estatísticas entre os grupos. Os RN do G2 e G3, com IG de entrada no estudo <32 semanas, iniciaram a alimentação VO mais precocemente do que os do grupo controle, no qual a idade ao iniciar VO foi de 34 semanas. Dentre os RN com estimulação da SNN, quanto menor a IG corrigida ao entrar no estudo, mais precoce foi o início da alimentação VO. CONCLUSÕES: A estimulação da SNN antecipou o início da alimentação VO, contribuindo para o desenvolvimento motor-oral e maturação do RN.

APA, Harvard, Vancouver, ISO, and other styles

35

Liu, Min, and Guangzhong Liu. "Prediction of Citrullination Sites on the Basis of mRMR Method and SNN." Combinatorial Chemistry & High Throughput Screening 22, no. 10 (January 16, 2020): 705–15. http://dx.doi.org/10.2174/1386207322666191129113508.

Full text

Abstract:

Background: Citrullination, an important post-translational modification of proteins, alters the molecular weight and electrostatic charge of the protein side chains. Citrulline, in protein sequences, is catalyzed by a class of Peptidyl Arginine Deiminases (PADs). Dependent on Ca2+, PADs include five isozymes: PAD 1, 2, 3, 4/5, and 6. Citrullinated proteins have been identified in many biological and pathological processes. Among them, abnormal protein citrullination modification can lead to serious human diseases, including multiple sclerosis and rheumatoid arthritis. Objective: It is important to identify the citrullination sites in protein sequences. The accurate identification of citrullination sites may contribute to the studies on the molecular functions and pathological mechanisms of related diseases. Methods and Results: In this study, after an encoded training set (containing 116 positive and 348 negative samples) into the feature matrix, the mRMR method was used to analyze the 941- dimensional features which were sorted on the basis of their importance. Then, a predictive model based on a self-normalizing neural network (SNN) was proposed to predict the citrullination sites in protein sequences. Incremental Feature Selection (IFS) and 10-fold cross-validation were used as the model evaluation method. Three classical machine learning models, namely random forest, support vector machine, and k-nearest neighbor algorithm, were selected and compared with the SNN prediction model using the same evaluation methods. SNN may be the best tool for citrullination site prediction. The maximum value of the Matthews Correlation Coefficient (MCC) reached 0.672404 on the basis of the optimal classifier of SNN. Conclusion: The results showed that the SNN-based prediction methods performed better when evaluated by some common metrics, such as MCC, accuracy, and F1-Measure. SNN prediction model also achieved a better balance in the classification and recognition of positive and negative samples from datasets compared with the other three models.

APA, Harvard, Vancouver, ISO, and other styles

36

Doborjeh, Maryam, Zohreh Doborjeh, Nikola Kasabov, Molood Barati, and Grace Y. Wang. "Deep Learning of Explainable EEG Patterns as Dynamic Spatiotemporal Clusters and Rules in a Brain-Inspired Spiking Neural Network." Sensors 21, no. 14 (July 19, 2021): 4900. http://dx.doi.org/10.3390/s21144900.

Full text

Abstract:

The paper proposes a new method for deep learning and knowledge discovery in a brain-inspired Spiking Neural Networks (SNN) architecture that enhances the model’s explainability while learning from streaming spatiotemporal brain data (STBD) in an incremental and on-line mode of operation. This led to the extraction of spatiotemporal rules from SNN models that explain why a certain decision (output prediction) was made by the model. During the learning process, the SNN created dynamic neural clusters, captured as polygons, which evolved in time and continuously changed their size and shape. The dynamic patterns of the clusters were quantitatively analyzed to identify the important STBD features that correspond to the most activated brain regions. We studied the trend of dynamically created clusters and their spike-driven events that occur together in specific space and time. The research contributes to: (1) enhanced interpretability of SNN learning behavior through dynamic neural clustering; (2) feature selection and enhanced accuracy of classification; (3) spatiotemporal rules to support model explainability; and (4) a better understanding of the dynamics in STBD in terms of feature interaction. The clustering method was applied to a case study of Electroencephalogram (EEG) data, recorded from a healthy control group (n = 21) and opiate use (n = 18) subjects while they were performing a cognitive task. The SNN models of EEG demonstrated different trends of dynamic clusters across the groups. This suggested to select a group of marker EEG features and resulted in an improved accuracy of EEG classification to 92%, when compared with all-feature classification. During learning of EEG data, the areas of neurons in the SNN model that form adjacent clusters (corresponding to neighboring EEG channels) were detected as fuzzy boundaries that explain overlapping activity of brain regions for each group of subjects.

APA, Harvard, Vancouver, ISO, and other styles

37

Wang, Hong-Qun, Zheng-Sheng Wu, and Dao-Wang Li. "Solitary Necrotic Nodule of the Liver: A Report of Two Cases and Review of the Literature." Case Reports in Hepatology 2011 (2011): 1–4. http://dx.doi.org/10.1155/2011/845406.

Full text

Abstract:

To investigate the clinicopathological characteristics and possible causes of solitary necrotic nodule of the liver (SNN), two cases of SNN of the liver were studied with clinicopathological data, immunohistochemistry, and histochemistry staining. The patients had no specific symptoms, with negative results for the serum tumor markers. CT and ultrasound all showed low-density lesion. Morphologically, there was isolate, single necrosis tubercle of the liver. It was composed of a central necrotic core and a peripheral fibrotic capsule with inflammatory cells, including histiocytes, plasma cells, lymphocytes, and so forth. The staining result of PAS, acid-fast, and iron was all negative, and AG + VG staining showed that the outline of reticular fibers and collagen was intact. Vimtin was positive for necrotic tissue and surrounding fibrous tissue. CD34 and CD68 was both positive for case 1. CK was negative in case 2 but positive for a few residual cells in case 1. SNN of the liver is a rare nonmalignant disease with a good prognosis. Hemangioma and fatty liver might be ones of the causes of SNN.

APA, Harvard, Vancouver, ISO, and other styles

38

Fang, Huijuan, Yongji Wang, and Jiping He. "Spiking Neural Networks for Cortical Neuronal Spike Train Decoding." Neural Computation 22, no. 4 (April 2010): 1060–85. http://dx.doi.org/10.1162/neco.2009.10-08-885.

Full text

Abstract:

Recent investigation of cortical coding and computation indicates that temporal coding is probably a more biologically plausible scheme used by neurons than the rate coding used commonly in most published work. We propose and demonstrate in this letter that spiking neural networks (SNN), consisting of spiking neurons that propagate information by the timing of spikes, are a better alternative to the coding scheme based on spike frequency (histogram) alone. The SNN model analyzes cortical neural spike trains directly without losing temporal information for generating more reliable motor command for cortically controlled prosthetics. In this letter, we compared the temporal pattern classification result from the SNN approach with results generated from firing-rate-based approaches: conventional artificial neural networks, support vector machines, and linear regression. The results show that the SNN algorithm can achieve higher classification accuracy and identify the spiking activity related to movement control earlier than the other methods. Both are desirable characteristics for fast neural information processing and reliable control command pattern recognition for neuroprosthetic applications.

APA, Harvard, Vancouver, ISO, and other styles

39

Chen, Ruizhi, and Ling Li. "Analyzing and Accelerating the Bottlenecks of Training Deep SNNs With Backpropagation." Neural Computation 32, no. 12 (December 2020): 2557–600. http://dx.doi.org/10.1162/neco_a_01319.

Full text

Abstract:

Spiking neural networks (SNNs) with the event-driven manner of transmitting spikes consume ultra-low power on neuromorphic chips. However, training deep SNNs is still challenging compared to convolutional neural networks (CNNs). The SNN training algorithms have not achieved the same performance as CNNs. In this letter, we aim to understand the intrinsic limitations of SNN training to design better algorithms. First, the pros and cons of typical SNN training algorithms are analyzed. Then it is found that the spatiotemporal backpropagation algorithm (STBP) has potential in training deep SNNs due to its simplicity and fast convergence. Later, the main bottlenecks of the STBP algorithm are analyzed, and three conditions for training deep SNNs with the STBP algorithm are derived. By analyzing the connection between CNNs and SNNs, we propose a weight initialization algorithm to satisfy the three conditions. Moreover, we propose an error minimization method and a modified loss function to further improve the training performance. Experimental results show that the proposed method achieves 91.53% accuracy on the CIFAR10 data set with 1% accuracy increase over the STBP algorithm and decreases the training epochs on the MNIST data set to 15 epochs (over 13 times speed-up compared to the STBP algorithm). The proposed method also decreases classification latency by over 25 times compared to the CNN-SNN conversion algorithms. In addition, the proposed method works robustly for very deep SNNs, while the STBP algorithm fails in a 19-layer SNN.

APA, Harvard, Vancouver, ISO, and other styles

40

Y.H. Ahmed, Falah, Yasir Hassan Ali, and Siti Mariyam Shamsuddin. "Using K-Fold Cross Validation Proposed Models for Spikeprop Learning Enhancements." International Journal of Engineering & Technology 7, no. 4.11 (October 2, 2018): 145. http://dx.doi.org/10.14419/ijet.v7i4.11.20790.

Full text

Abstract:

Spiking Neural Network (SNN) uses individual spikes in time field to perform as well as to communicate computation in such a way as the actual neurons act. SNN was not studied earlier as it was considered too complicated and too hard to examine. Several limitations concerning the characteristics of SNN which were not researched earlier are now resolved since the introduction of SpikeProp in 2000 by Sander Bothe as a supervised SNN learning model. This paper defines the research developments of the enhancement Spikeprop learning using K-fold cross validation for datasets classification. Hence, this paper introduces acceleration factors of SpikeProp using Radius Initial Weight and Differential Evolution (DE) Initialization weights as proposed methods. In addition, training and testing using K-fold cross validation properties of the new proposed method were investigated using datasets obtained from Machine Learning Benchmark Repository as an improved Bohte’s algorithm. A comparison of the performance was made between the proposed method and Backpropagation (BP) together with the Standard SpikeProp. The findings also reveal that the proposed method has better performance when compared to Standard SpikeProp as well as the BP for all datasets performed by K-fold cross validation for classification datasets.

APA, Harvard, Vancouver, ISO, and other styles

41

SCHLIEBS, STEFAN, NIKOLA KASABOV, and MICHAËL DEFOIN-PLATEL. "ON THE PROBABILISTIC OPTIMIZATION OF SPIKING NEURAL NETWORKS." International Journal of Neural Systems 20, no. 06 (December 2010): 481–500. http://dx.doi.org/10.1142/s0129065710002565.

Full text

Abstract:

The construction of a Spiking Neural Network (SNN), i.e. the choice of an appropriate topology and the configuration of its internal parameters, represents a great challenge for SNN based applications. Evolutionary Algorithms (EAs) offer an elegant solution for these challenges and methods capable of exploring both types of search spaces simultaneously appear to be the most promising ones. A variety of such heterogeneous optimization algorithms have emerged recently, in particular in the field of probabilistic optimization. In this paper, a literature review on heterogeneous optimization algorithms is presented and an example of probabilistic optimization of SNN is discussed in detail. The paper provides an experimental analysis of a novel Heterogeneous Multi-Model Estimation of Distribution Algorithm (hMM-EDA). First, practical guidelines for configuring the method are derived and then the performance of hMM-EDA is compared to state-of-the-art optimization algorithms. Results show hMM-EDA as a light-weight, fast and reliable optimization method that requires the configuration of only very few parameters. Its performance on a synthetic heterogeneous benchmark problem is highly competitive and suggests its suitability for the optimization of SNN.

APA, Harvard, Vancouver, ISO, and other styles

42

Chen, Boquan, Elena D’Onghia, João Alves, and Angela Adamo. "Discovery of new stellar groups in the Orion complex." Astronomy & Astrophysics 643 (November 2020): A114. http://dx.doi.org/10.1051/0004-6361/201935955.

Full text

Abstract:

We test the ability of two unsupervised machine learning algorithms, EnLink and Shared Nearest Neighbor (SNN), to identify stellar groupings in the Orion star-forming complex as an application to the 5D astrometric data from Gaia DR2. The algorithms represent two distinct approaches to limiting user bias when selecting parameter values and evaluating the relative weights among astrometric parameters. EnLink adopts a locally adaptive distance metric and eliminates the need for parameter tuning through automation. The original SNN relies only on human input for parameter tuning so we modified SNN to run in two stages. We first ran the original SNN 7000 times, each with a randomly generated sample according to within-source co-variance matrices provided in Gaia DR2 and random parameter values within reasonable ranges. During the second stage, we modified SNN to identify the most repeating stellar groups from the 25 798 we obtained in the first stage. We recovered 22 spatially and kinematically coherent groups in the Orion complex, 12 of which were previously unknown. The groups show a wide distribution of distances extending as far as about 150 pc in front of the star-forming Orion molecular clouds, to about 50 pc beyond them, where we, unexpectedly, find several groups. Our results reveal the wealth of sub-structure in the OB association, within and beyond the classical Blaauw Orion OBI sub-groups. A full characterization of the new groups is essential as it offers the potential to unveil how star formation proceeds globally in large complexes such as Orion.

APA, Harvard, Vancouver, ISO, and other styles

43

Mukhopadhyay, Anand Kumar, Atul Sharma, Indrajit Chakrabarti, Arindam Basu, and Mrigank Sharad. "Power-efficient Spike Sorting Scheme Using Analog Spiking Neural Network Classifier." ACM Journal on Emerging Technologies in Computing Systems 17, no. 2 (April 2021): 1–29. http://dx.doi.org/10.1145/3432814.

Full text

Abstract:

The method to map the neural signals to the neuron from which it originates is spike sorting. A low-power spike sorting system is presented for a neural implant device. The spike sorter constitutes a two-step trainer module that is shared by the signal acquisition channel associated with multiple electrodes. A low-power Spiking Neural Network (SNN) module is responsible for assigning the spike class. The two-step shared supervised on-chip training module is presented for improved training accuracy for the SNN. Post implant, the relatively power-hungry training module can be activated conditionally based on a statistics-driven retraining algorithm that allows on the fly training and adaptation. A low-power analog implementation for the SNN classifier is proposed based on resistive crossbar memory exploiting its approximate computing nature. Owing to the direct mapping of SNN functionality using physical characteristics of devices, the analog mode implementation can achieve ∼21 × lower power than its fully digital counterpart. We also incorporate the effect of device variation in the training process to suppress the impact of inevitable inaccuracies in such resistive crossbar devices on the classification accuracy. A variation-aware, digitally calibrated analog front-end is also presented, which consumes less than ∼50 nW power and interfaces with the digital training module as well as the analog SNN spike sorting module. Hence, the proposed scheme is a low-power, variation-tolerant, adaptive, digitally trained, all-analog spike sorter device, applicable to implantable and wearable multichannel brain-machine interfaces.

APA, Harvard, Vancouver, ISO, and other styles

44

Mo, Lingfei, Xinao Chen, and Gang Wang. "EDHA: Event-Driven High Accurate Simulator for Spike Neural Networks." Electronics 10, no. 18 (September 17, 2021): 2281. http://dx.doi.org/10.3390/electronics10182281.

Full text

Abstract:

In recent years, spiking neural networks (SNNs) have attracted increasingly more researchers to study by virtue of its bio-interpretability and low-power computing. The SNN simulator is an essential tool to accomplish image classification, recognition, speech recognition, and other tasks using SNN. However, most of the existing simulators for spike neural networks are clock-driven, which has two main problems. First, the calculation result is affected by time slice, which obviously shows that when the calculation accuracy is low, the calculation speed is fast, but when the calculation accuracy is high, the calculation speed is unacceptable. The other is the failure of lateral inhibition, which severely affects SNN learning. In order to solve these problems, an event-driven high accurate simulator named EDHA (Event-Driven High Accuracy) for spike neural networks is proposed in this paper. EDHA takes full advantage of the event-driven characteristics of SNN and only calculates when a spike is generated, which is independent of the time slice. Compared with previous SNN simulators, EDHA is completely event-driven, which reduces a large amount of calculations and achieves higher computational accuracy. The calculation speed of EDHA in the MNIST classification task is more than 10 times faster than that of mainstream clock-driven simulators. By optimizing the spike encoding method, the former can even achieve more than 100 times faster than the latter. Due to the cross-platform characteristics of Java, EDHA can run on x86, amd64, ARM, and other platforms that support Java.

APA, Harvard, Vancouver, ISO, and other styles

45

Clark, Michael. "Femtoscopy in √SNN= 5.02 TeVp-Pb collisions withATLAS." EPJ Web of Conferences 141 (2017): 01013. http://dx.doi.org/10.1051/epjconf/201714101013.

Full text

APA, Harvard, Vancouver, ISO, and other styles

46

Trentin, Edmondo, and Marco Matassoni. "Noise-tolerant speech recognition: the SNN-TA approach." Information Sciences 156, no. 1-2 (November 2003): 55–69. http://dx.doi.org/10.1016/s0020-0255(03)00164-6.

Full text

APA, Harvard, Vancouver, ISO, and other styles

47

Guo, Shasha, Lei Wang, Baozi Chen, and Qiang Dou. "An Overhead-Free Max-Pooling Method for SNN." IEEE Embedded Systems Letters 12, no. 1 (March 2020): 21–24. http://dx.doi.org/10.1109/les.2019.2919244.

Full text

APA, Harvard, Vancouver, ISO, and other styles

48

Shi, Zhaozhong. "D0-Meson R in PbPb Collisions at sNN=5.02TeV and Elliptic Flow in pPb Collisions at sNN=8.16TeV with CMS." Nuclear Physics A 982 (February 2019): 647–50. http://dx.doi.org/10.1016/j.nuclphysa.2018.08.029.

Full text

APA, Harvard, Vancouver, ISO, and other styles

49

Han, Yulan, and Chongzhao Han. "Two Measurement Set Partitioning Algorithms for the Extended Target Probability Hypothesis Density Filter." Sensors 19, no. 12 (June 13, 2019): 2665. http://dx.doi.org/10.3390/s19122665.

Full text

Abstract:

The extended target probability hypothesis density (ET-PHD) filter cannot work well if the density of measurements varies from target to target, which is based on the measurement set partitioning algorithms employing the Mahalanobis distance between measurements. To tackle the problem, two measurement set partitioning approaches, the shared nearest neighbors similarity partitioning (SNNSP) and SNN density partitioning (SNNDP), are proposed in this paper. In SNNSP, the shared nearest neighbors (SNN) similarity, which incorporates the neighboring measurement information, is introduced to DP instead of the Mahalanobis distance between measurements. Furthermore, the SNNDP is developed by combining the DBSCAN algorithm with the SNN similarity together to enhance the reliability of partitions. Simulation results show that the ET-PHD filters based on the two proposed partitioning algorithms can achieve better tracking performance with less computation than the compared algorithms.

APA, Harvard, Vancouver, ISO, and other styles

50

Lee, Sung-Tae, Suhwan Lim, Jong-Ho Bae, Dongseok Kwon, Hyeong-Su Kim, Byung-Gook Park, and Jong-Ho Lee. "Pruning for Hardware-Based Deep Spiking Neural Networks Using Gated Schottky Diode as Synaptic Devices." Journal of Nanoscience and Nanotechnology 20, no. 11 (November 1, 2020): 6603–8. http://dx.doi.org/10.1166/jnn.2020.18772.

Full text

Abstract:

Deep learning represents state-of-the-art results in various machine learning tasks, but for applications that require real-time inference, the high computational cost of deep neural networks becomes a bottleneck for the efficiency. To overcome the high computational cost of deep neural networks, spiking neural networks (SNN) have been proposed. Herein, we propose a hardware implementation of the SNN with gated Schottky diodes as synaptic devices. In addition, we apply L1 regularization for connection pruning of the deep spiking neural networks using gated Schottky diodes as synap-tic devices. Applying L1 regularization eliminates the need for a re-training procedure because it prunes the weights based on the cost function. The compressed hardware-based SNN is energy efficient while achieving a classification accuracy of 97.85% which is comparable to 98.13% of the software deep neural networks (DNN).

APA, Harvard, Vancouver, ISO, and other styles

Journal articles on the topic 'SNN'

Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles