To see the other types of publications on this topic, follow the link: Neural networks; Visual information.
Journal articles on the topic 'Neural networks; Visual information'
Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles
Consult the top 50 journal articles for your research on the topic 'Neural networks; Visual information.'
Next to every source in the list of references, there is an 'Add to bibliography' button. Press on it, and we will generate automatically the bibliographic reference to the chosen work in the citation style you need: APA, MLA, Harvard, Chicago, Vancouver, etc.
You can also download the full text of the academic publication as pdf and read online its abstract whenever available in the metadata.
Browse journal articles on a wide variety of disciplines and organise your bibliography correctly.
1
Hertz, J. A., T. W. Kjær, E. N. Eskandar, and B. J. Richmond. "MEASURING NATURAL NEURAL PROCESSING WITH ARTIFICIAL NEURAL NETWORKS." International Journal of Neural Systems 03, supp01 (1992): 91–103. http://dx.doi.org/10.1142/s0129065792000425.
Full textAbstract:
We show how to use artificial neural networks as a quantitative tool in studying real neuronal processing in the monkey visual system. Training a network to classify neuronal signals according to the stimulus that elicited them permits us to calculate the information transmitted by these signals. We illustrate this for neurons in the primary visual cortex with measurements of the information transmitted about visual stimuli and for cells in inferior temporal cortex with measurements of information about behavioral context. For the latter neurons we also illustrate how artificial neural networks can be used to model the computation they do.
2
Kawato, Mitsuo, Takatoshi Ikeda, and Sei Miyake. "Learning in neural networks for visual information processing." Journal of the Institute of Television Engineers of Japan 42, no. 9 (1988): 918–24. http://dx.doi.org/10.3169/itej1978.42.918.
Full text
3
Seeland, Marco, and Patrick Mäder. "Multi-view classification with convolutional neural networks." PLOS ONE 16, no. 1 (2021): e0245230. http://dx.doi.org/10.1371/journal.pone.0245230.
Full textAbstract:
Humans’ decision making process often relies on utilizing visual information from different views or perspectives. However, in machine-learning-based image classification we typically infer an object’s class from just a single image showing an object. Especially for challenging classification problems, the visual information conveyed by a single image may be insufficient for an accurate decision. We propose a classification scheme that relies on fusing visual information captured through images depicting the same object from multiple perspectives. Convolutional neural networks are used to extract and encode visual features from the multiple views and we propose strategies for fusing these information. More specifically, we investigate the following three strategies: (1) fusing convolutional feature maps at differing network depths; (2) fusion of bottleneck latent representations prior to classification; and (3) score fusion. We systematically evaluate these strategies on three datasets from different domains. Our findings emphasize the benefit of integrating information fusion into the network rather than performing it by post-processing of classification scores. Furthermore, we demonstrate through a case study that already trained networks can be easily extended by the best fusion strategy, outperforming other approaches by large margin.
4
MAINZER, KLAUS. "CELLULAR NEURAL NETWORKS AND VISUAL COMPUTING." International Journal of Bifurcation and Chaos 13, no. 01 (2003): 1–6. http://dx.doi.org/10.1142/s0218127403006534.
Full textAbstract:
Brain-like information processing has become a challenge to modern computer science and chip technology. The CNN (Cellular Neural Network) Universal Chip is the first fully programmable industrial-sized brain-like stored-program dynamic array computer which dates back to an invention of Leon O. Chua and Lin Yang in Berkeley in 1988. Since then, many papers have been written on the mathematical foundations and technical applications of CNN chips. They are already used to model artificial, physical, chemical, as well as living biological systems. CNN is now a new computing paradigm of interdisciplinary interest. In this state of development a textbook is needed in order to recruit new generations of students and researchers from different fields of research. Thus, Chua's and Roska's textbook is a timely and historic publication. On the background of their teaching experience, they have aimed at undergraduate students from engineering, physics, chemistry, as well as biology departments. But, actually, it offers more. It is a brilliant introduction to the foundations and applications of CNN which is distinguished with conceptual and mathematical precision as well as with detailed explanations of applications in visual computing.
5
Hartono, Pitoyo. "A transparent cancer classifier." Health Informatics Journal 26, no. 1 (2018): 190–204. http://dx.doi.org/10.1177/1460458218817800.
Full textAbstract:
Recently, many neural network models have been successfully applied for histopathological analysis, including for cancer classifications. While some of them reach human–expert level accuracy in classifying cancers, most of them have to be treated as black box, in which they do not offer explanation on how they arrived at their decisions. This lack of transparency may hinder the further applications of neural networks in realistic clinical settings where not only decision but also explainability is important. This study proposes a transparent neural network that complements its classification decisions with visual information about the given problem. The auxiliary visual information allows the user to some extent understand how the neural network arrives at its decision. The transparency potentially increases the usability of neural networks in realistic histopathological analysis. In the experiment, the accuracy of the proposed neural network is compared against some existing classifiers, and the visual information is compared against some dimensional reduction methods.
6
Et. al., K. P. Moholkar,. "Visual Question Answering using Convolutional Neural Networks." Turkish Journal of Computer and Mathematics Education (TURCOMAT) 12, no. 1S (2021): 170–75. http://dx.doi.org/10.17762/turcomat.v12i1s.1602.
Full textAbstract:
The ability of a computer system to be able to understand surroundings and elements and to think like a human being to process the information has always been the major point of focus in the field of Computer Science. One of the ways to achieve this artificial intelligence is Visual Question Answering. Visual Question Answering (VQA) is a trained system which can answer the questions associated to a given image in Natural Language. VQA is a generalized system which can be used in any image-based scenario with adequate training on the relevant data. This is achieved with the help of Neural Networks, particularly Convolutional Neural Network (CNN) and Recurrent Neural Network (RNN). In this study, we have compared different approaches of VQA, out of which we are exploring CNN based model. With the continued progress in the field of Computer Vision and Question answering system, Visual Question Answering is becoming the essential system which can handle multiple scenarios with their respective data.
7
Deng, Yu Qiao, and Ge Song. "A Verifiable Visual Cryptography Scheme Using Neural Networks." Advanced Materials Research 756-759 (September 2013): 1361–65. http://dx.doi.org/10.4028/www.scientific.net/amr.756-759.1361.
Full textAbstract:
This paper proposes a new verifiable visual cryptography scheme for general access structures using pi-sigma neural networks (VVCSPSN), which is based on probabilistic signature scheme (PSS), which is considered as security and effective verification method. Compared to other high-order networks, PSN has a highly regular structure, needs a much smaller number of weights and less training time. Using PSNs capability of large-scale parallel classification, VCSPSN reduces the information communication rate greatly, makes best known upper bound polynomial, and distinguishes the deferent information in secret image.
8
Merilaita, Sami. "Artificial neural networks and the study of evolution of prey coloration." Philosophical Transactions of the Royal Society B: Biological Sciences 362, no. 1479 (2007): 421–30. http://dx.doi.org/10.1098/rstb.2006.1969.
Full textAbstract:
In this paper, I investigate the use of artificial neural networks in the study of prey coloration. I briefly review the anti-predator functions of prey coloration and describe both in general terms and with help of two studies as specific examples the use of neural network models in the research on prey coloration. The first example investigates the effect of visual complexity of background on evolution of camouflage. The second example deals with the evolutionary choice of defence strategy, crypsis or aposematism. I conclude that visual information processing by predators is central in evolution of prey coloration. Therefore, the capability to process patterns as well as to imitate aspects of predator's information processing and responses to visual information makes neural networks a well-suited modelling approach for the study of prey coloration. In addition, their suitability for evolutionary simulations is an advantage when complex or dynamic interactions are modelled. Since not all behaviours of neural network models are necessarily biologically relevant, it is important to validate a neural network model with empirical data. Bringing together knowledge about neural networks with knowledge about topics of prey coloration would provide a potential way to deepen our understanding of the specific appearances of prey coloration.
9
Wolfrum, Philipp, and Christoph von der Malsburg. "What Is the Optimal Architecture for Visual Information Routing?" Neural Computation 19, no. 12 (2007): 3293–309. http://dx.doi.org/10.1162/neco.2007.19.12.3293.
Full textAbstract:
Analyzing the design of networks for visual information routing is an underconstrained problem due to insufficient anatomical and physiological data. We propose here optimality criteria for the design of routing networks. For a very general architecture, we derive the number of routing layers and the fanout that minimize the required neural circuitry. The optimal fanout l is independent of network size, while the number k of layers scales logarithmically (with a prefactor below 1), with the number n of visual resolution units to be routed independently. The results are found to agree with data of the primate visual system.
10
Medvedev, Viktor, Gintautas Dzemyda, Olga Kurasova, and Virginijus Marcinkevičius. "Efficient Data Projection for Visual Analysis of Large Data Sets Using Neural Networks." Informatica 22, no. 4 (2011): 507–20. http://dx.doi.org/10.15388/informatica.2011.339.
Full text
11
Majerus, Steve, Arnaud D'Argembeau, Trecy Martinez Perez, et al. "The Commonality of Neural Networks for Verbal and Visual Short-term Memory." Journal of Cognitive Neuroscience 22, no. 11 (2010): 2570–93. http://dx.doi.org/10.1162/jocn.2009.21378.
Full textAbstract:
Although many neuroimaging studies have considered verbal and visual short-term memory (STM) as relying on neurally segregated short-term buffer systems, the present study explored the existence of shared neural correlates supporting verbal and visual STM. We hypothesized that networks involved in attentional and executive processes, as well as networks involved in serial order processing, underlie STM for both verbal and visual list information, with neural specificity restricted to sensory areas involved in processing the specific items to be retained. Participants were presented sequences of nonwords or unfamiliar faces, and were instructed to maintain and recognize order or item information. For encoding and retrieval phases, null conjunction analysis revealed an identical fronto-parieto-cerebellar network comprising the left intraparietal sulcus, bilateral dorsolateral prefrontal cortex, and the bilateral cerebellum, irrespective of information type and modality. A network centered around the right intraparietal sulcus supported STM for order information, in both verbal and visual modalities. Modality-specific effects were observed in left superior temporal and mid-fusiform areas associated with phonological and orthographic processing during the verbal STM tasks, and in right hippocampal and fusiform face processing areas during the visual STM tasks, wherein these modality effects were most pronounced when storing item information. The present results suggest that STM emerges from the deployment of modality-independent attentional and serial ordering processes toward sensory networks underlying the processing and storage of modality-specific item information.
12
YANG, SIMON X. "VISUAL INFORMATION ACQUISITION IN VERTEBRATE RETINA." International Journal of Information Acquisition 01, no. 01 (2004): 67–76. http://dx.doi.org/10.1142/s0219878904000033.
Full textAbstract:
In this paper, visual information acquisition in vertebrate retina is investigated using a novel neural network model. The neural network is based on the neural anatomy and function of retinal neurons in tiger salamander and mudpuppy. All the main types of retinal neurons are modeled, and their response characteristics are studied. The objective is to model the information acquisition in vertebrate retina with a simple yet effective neural network architecture. The model predictions on the main characteristics of retinal neurons are in agreement with the neurophysiological data. This study not only offers insight into the biological strategy and mechanism on the early visual information acquisition in vertebrate retina, but also has potential industrial applications such as VLSI chip design for efficient visual and movement sensors.
13
Al-Tahan, Haider, and Yalda Mohsenzadeh. "Reconstructing feedback representations in the ventral visual pathway with a generative adversarial autoencoder." PLOS Computational Biology 17, no. 3 (2021): e1008775. http://dx.doi.org/10.1371/journal.pcbi.1008775.
Full textAbstract:
While vision evokes a dense network of feedforward and feedback neural processes in the brain, visual processes are primarily modeled with feedforward hierarchical neural networks, leaving the computational role of feedback processes poorly understood. Here, we developed a generative autoencoder neural network model and adversarially trained it on a categorically diverse data set of images. We hypothesized that the feedback processes in the ventral visual pathway can be represented by reconstruction of the visual information performed by the generative model. We compared representational similarity of the activity patterns in the proposed model with temporal (magnetoencephalography) and spatial (functional magnetic resonance imaging) visual brain responses. The proposed generative model identified two segregated neural dynamics in the visual brain. A temporal hierarchy of processes transforming low level visual information into high level semantics in the feedforward sweep, and a temporally later dynamics of inverse processes reconstructing low level visual information from a high level latent representation in the feedback sweep. Our results append to previous studies on neural feedback processes by presenting a new insight into the algorithmic function and the information carried by the feedback processes in the ventral visual pathway.
14
Moskvin, A. A., and A. G. Shishkin. "Deep Learning Based Human Emotional State Recognition in a Video." Journal of Modeling and Optimization 12, no. 1 (2020): 51–59. http://dx.doi.org/10.32732/jmo.2020.12.1.51.
Full textAbstract:
Human emotions play significant role in everyday life. There are a lot of applications of automatic emotion recognition in medicine, e-learning, monitoring, marketing etc. In this paper the method and neural network architecture for real-time human emotion recognition by audio-visual data are proposed. To classify one of seven emotions, deep neural networks, namely, convolutional and recurrent neural networks are used. Visual information is represented by a sequence of 16 frames of 96 × 96 pixels, and audio information - by 140 features for each of a sequence of 37 temporal windows. To reduce the number of audio features autoencoder was used. Audio information in conjunction with visual one is shown to increase recognition accuracy up to 12%. The developed system being not demanding to be computing resources is dynamic in terms of selection of parameters, reducing or increasing the number of emotion classes, as well as the ability to easily add, accumulate and use information from other external devices for further improvement of classification accuracy.
15
Anderson, Dana Z. "Material Demands for Optical Neural Networks." MRS Bulletin 13, no. 8 (1988): 30–35. http://dx.doi.org/10.1557/s0883769400064654.
Full textAbstract:
From the time of their conception, holography and holograms have evolved as a metaphor for human memory. Holograms can be made so that the information they contain is distributed throughout the holographic medium—destroy part of the hologram and the stored information remains wholly intact, except for a loss of detail. In this property holograms evidently have something in common with human memory, which is to some extent resilient against physical damage to the brain. There is much more to the metaphor than simply that information is stored in a distributed manner.Research in the optics community is now looking to holography, in particular dynamic holography, not only for information storage, but for information processing as well. The ideas are based upon neural network models. Neural networks are models for processing that are inspired by the apparent architecture of the brain. This is a processing paradigm that is new to optics. From within this network paradigm we look to build machines that can store and recall information associatively, play back a chain of recorded events, undergo learning and possibly forgetting, make decisions, adapt to a particular environment, and self-organize to evolve some desirable behavior. We hope that neural network models will give rise to optical machines for memory, speech processing, visual processing, language acquisition, motor control, and so on.
16
Medina, José M. "Effects of Multiplicative Power Law Neural Noise in Visual Information Processing." Neural Computation 23, no. 4 (2011): 1015–46. http://dx.doi.org/10.1162/neco_a_00102.
Full textAbstract:
The human visual system is intrinsically noisy. The benefits of internal noise as part of visual code are controversial. Here the information-theoretic properties of multiplicative (i.e. signal-dependent) neural noise are investigated. A quasi-linear communication channel model is presented. The model shows that multiplicative power law neural noise promotes the minimum information transfer after efficient coding. It is demonstrated that Weber's law and the human contrast sensitivity function arise on the basis of minimum transfer of information and power law neural noise. The implications of minimum information transfer in self-organized neural networks and weakly coupled neurons are discussed.
17
Ceroni, Andrea, Chenyang Ma, and Ralph Ewerth. "Mining exoticism from visual content with fusion-based deep neural networks." International Journal of Multimedia Information Retrieval 8, no. 1 (2019): 19–33. http://dx.doi.org/10.1007/s13735-018-00165-4.
Full text
18
Cosi, P., M. Dugatto, F. Ferrero, E. Magno Caldognetto, and K. Vagges. "Phonetic recognition by recurrent neural networks working on audio and visual information." Speech Communication 19, no. 3 (1996): 245–52. http://dx.doi.org/10.1016/0167-6393(96)00034-9.
Full text
19
KATAYAMA, Masazumi, and Mitsuo KAWATO. "Neural network model integrating visual and somatic information." Journal of the Robotics Society of Japan 8, no. 6 (1990): 757–65. http://dx.doi.org/10.7210/jrsj.8.6_757.
Full text
20
LAGHARI, M. S., and A. BOUJARWAH. "WEAR PARTICLE TEXTURE CLASSIFICATION USING ARTIFICIAL NEURAL NETWORKS." International Journal of Pattern Recognition and Artificial Intelligence 13, no. 03 (1999): 415–28. http://dx.doi.org/10.1142/s0218001499000240.
Full textAbstract:
Analysis of wear debris carried by a lubricant in an oil-wetted system provides important information about the condition of a machine. This paper describes the analysis of microscopic metal particles generated by wear using computer vision and image processing. The aim is to classify these particles according to their morphology and surface texture and by using the information obtained, to predict wear failure modes in engines and other machinery. This approach obviates the need for specialists and reliance on human visual inspection techniques. The procedure reported in this paper, is used to classify surface features of the wear particles by using artificial neural networks. A visual comparison between cooccurrence matrices representing five different texture classes is described. Based on these comparisons, matrices of reduced sizes are utilized to train a feed-forward neural classifier in order to distinguish between the various texture classes.
21
Kang, Byeongkeun, and Yeejin Lee. "High-Resolution Neural Network for Driver Visual Attention Prediction." Sensors 20, no. 7 (2020): 2030. http://dx.doi.org/10.3390/s20072030.
Full textAbstract:
Driving is a task that puts heavy demands on visual information, thereby the human visual system plays a critical role in making proper decisions for safe driving. Understanding a driver’s visual attention and relevant behavior information is a challenging but essential task in advanced driver-assistance systems (ADAS) and efficient autonomous vehicles (AV). Specifically, robust prediction of a driver’s attention from images could be a crucial key to assist intelligent vehicle systems where a self-driving car is required to move safely interacting with the surrounding environment. Thus, in this paper, we investigate a human driver’s visual behavior in terms of computer vision to estimate the driver’s attention locations in images. First, we show that feature representations at high resolution improves visual attention prediction accuracy and localization performance when being fused with features at low-resolution. To demonstrate this, we employ a deep convolutional neural network framework that learns and extracts feature representations at multiple resolutions. In particular, the network maintains the feature representation with the highest resolution at the original image resolution. Second, attention prediction tends to be biased toward centers of images when neural networks are trained using typical visual attention datasets. To avoid overfitting to the center-biased solution, the network is trained using diverse regions of images. Finally, the experimental results verify that our proposed framework improves the prediction accuracy of a driver’s attention locations.
22
Moyal, Roy, and Shimon Edelman. "Dynamic Computation in Visual Thalamocortical Networks." Entropy 21, no. 5 (2019): 500. http://dx.doi.org/10.3390/e21050500.
Full textAbstract:
Contemporary neurodynamical frameworks, such as coordination dynamics and winnerless competition, posit that the brain approximates symbolic computation by transitioning between metastable attractive states. This article integrates these accounts with electrophysiological data suggesting that coherent, nested oscillations facilitate information representation and transmission in thalamocortical networks. We review the relationship between criticality, metastability, and representational capacity, outline existing methods for detecting metastable oscillatory patterns in neural time series data, and evaluate plausible spatiotemporal coding schemes based on phase alignment. We then survey the circuitry and the mechanisms underlying the generation of coordinated alpha and gamma rhythms in the primate visual system, with particular emphasis on the pulvinar and its role in biasing visual attention and awareness. To conclude the review, we begin to integrate this perspective with longstanding theories of consciousness and cognition.
23
Reddy*, M. Venkata Krishna, and Pradeep S. "Envision Foundational of Convolution Neural Network." International Journal of Innovative Technology and Exploring Engineering 10, no. 6 (2021): 54–60. http://dx.doi.org/10.35940/ijitee.f8804.0410621.
Full textAbstract:
1. Bilal, A. Jourabloo, M. Ye, X. Liu, and L. Ren. Do Convolutional Neural Networks Learn Class Hierarchy? IEEE Transactions on Visualization and Computer Graphics, 24(1):152–162, Jan. 2018. 2. M. Carney, B. Webster, I. Alvarado, K. Phillips, N. Howell, J. Griffith, J. Jongejan, A. Pitaru, and A. Chen. Teachable Machine: Approachable Web-Based Tool for Exploring Machine Learning Classification. In Extended Abstracts of the 2020 CHI Conference on Human Factors in Computing Systems, CHI ’20. ACM, Honolulu, HI, USA, 2020. 3. A. Karpathy. CS231n Convolutional Neural Networks for Visual Recognition, 2016 4. M. Kahng, N. Thorat, D. H. Chau, F. B. Viegas, and M. Wattenberg. GANLab: Understanding Complex Deep Generative Models using Interactive Visual Experimentation. IEEE Transactions on Visualization and Computer Graphics, 25(1):310–320, Jan. 2019. 5. J. Yosinski, J. Clune, A. Nguyen, T. Fuchs, and H. Lipson. Understanding Neural Networks Through Deep Visualization. In ICML Deep Learning Workshop, 2015 6. M. Kahng, P. Y. Andrews, A. Kalro, and D. H. Chau. ActiVis: Visual Exploration of Industry-Scale Deep Neural Network Models. IEEE Transactions on Visualization and Computer Graphics, 24(1):88–97, Jan. 2018. 7. https://cs231n.github.io/convolutional-networks/ 8. https://www.analyticsvidhya.com/blog/2020/02/learn-imageclassification-cnn-convolutional-neural-networks-3-datasets/ 9. https://towardsdatascience.com/understanding-cnn-convolutionalneural- network-69fd626ee7d4 10. https://medium.com/@birdortyedi_23820/deep-learning-lab-episode-2- cifar- 10-631aea84f11e 11. J. Gu, Z. Wang, J. Kuen, L. Ma, A. Shahroudy, B. Shuai, T. Liu, X. Wang, G. Wang, J. Cai, and T. Chen. Recent advances in convolutional neural networks. Pattern Recognition, 77:354–377, May 2018. 12. Hamid, Y., Shah, F.A. and Sugumaram, M. (2014), ―Wavelet neural network model for network intrusion detection system‖, International Journal of Information Technology, Vol. 11 No. 2, pp. 251-263 13. G Sreeram , S Pradeep, K SrinivasRao , B.Deevan Raju , Parveen Nikhat , ― Moving ridge neuronal espionage network simulation for reticulum invasion sensing‖. International Journal of Pervasive Computing and Communications.https://doi.org/10.1108/IJPCC-05- 2020-0036 14. E. Stevens, L. Antiga, and T. Viehmann. Deep Learning with PyTorch. O’Reilly Media, 2019. 15. J. Yosinski, J. Clune, A. Nguyen, T. Fuchs, and H. Lipson. Understanding Neural Networks Through Deep Visualization. In ICML Deep Learning Workshop, 2015. 16. Aman Dureja, Payal Pahwa, ―Analysis of Non-Linear Activation Functions for Classification Tasks Using Convolutional Neural Networks‖, Recent Advances in Computer Science , Vol 2, Issue 3, 2019 ,PP-156-161 17. https://missinglink.ai/guides/neural-network-concepts/7-types-neuralnetwork-activation-functions-right/
24
MARSHALL, JONATHAN A., and VISWANATH SRIKANTH. "CURVED TRAJECTORY PREDICTION USING A SELF-ORGANIZING NEURAL NETWORK." International Journal of Neural Systems 10, no. 01 (2000): 59–70. http://dx.doi.org/10.1142/s0129065700000065.
Full textAbstract:
Existing neural network models are capable of tracking linear trajectories of moving visual objects. This paper describes an additional neural mechanism, disfacilitation, that enhances the ability of a visual system to track curved trajectories. The added mechanism combines information about an object's trajectory with information about changes in the object's trajectory, to improve the estimates for the object's next probable location. Computational simulations are presented that show how the neural mechanism can learn to track the speed of objects and how the network operates to predict the trajectories of accelerating and decelerating objects.
25
Kádár, Ákos, Grzegorz Chrupała, and Afra Alishahi. "Representation of Linguistic Form and Function in Recurrent Neural Networks." Computational Linguistics 43, no. 4 (2017): 761–80. http://dx.doi.org/10.1162/coli_a_00300.
Full textAbstract:
We present novel methods for analyzing the activation patterns of recurrent neural networks from a linguistic point of view and explore the types of linguistic structure they learn. As a case study, we use a standard standalone language model, and a multi-task gated recurrent network architecture consisting of two parallel pathways with shared word embeddings: The Visual pathway is trained on predicting the representations of the visual scene corresponding to an input sentence, and the Textual pathway is trained to predict the next word in the same sentence. We propose a method for estimating the amount of contribution of individual tokens in the input to the final prediction of the networks. Using this method, we show that the Visual pathway pays selective attention to lexical categories and grammatical functions that carry semantic information, and learns to treat word types differently depending on their grammatical function and their position in the sequential structure of the sentence. In contrast, the language models are comparatively more sensitive to words with a syntactic function. Further analysis of the most informative n-gram contexts for each model shows that in comparison with the Visual pathway, the language models react more strongly to abstract contexts that represent syntactic constructions.
26
Wai Yong, Ching, Kareen Teo, Belinda Pingguan Murphy, Yan Chai Hum, and Khin Wee Lai. "CORSegNet: Deep Neural Network for Core Object Segmentation on Medical Images." Journal of Medical Imaging and Health Informatics 11, no. 5 (2021): 1364–71. http://dx.doi.org/10.1166/jmihi.2021.3380.
Full textAbstract:
In recent decades, convolutional neural networks (CNNs) have delivered promising results in vision-related tasks across different domains. Previous studies have introduced deeper network architectures to further improve the performances of object classification, localization, and segmentation. However, this induces the complexity in mapping network’s layer to the processing elements in the ventral visual pathway. Although CORnet models are not precisely biomimetic, they are closer approximations to the anatomy of ventral visual pathway compared with other deep neural networks. The uniqueness of this architecture inspires us to extend it into a core object segmentation network, CORSegnet-Z. This architecture utilizes CORnet-Z building blocks as the encoding elements. We train and evaluate the proposed model using two large datasets. Our proposed model shows significant improvements on the segmentation metrics in delineating cartilage tissues from knee magnetic resonance (MR) images and segmenting lesion boundary from dermoscopic images.
27
Chu, Wei-Ta, Yu-Hsuan Liang, and Kai-Chia Ho. "Visual Weather Property Prediction by Multi-Task Learning and Two-Dimensional RNNs." Atmosphere 12, no. 5 (2021): 584. http://dx.doi.org/10.3390/atmos12050584.
Full textAbstract:
We attempted to employ convolutional neural networks to extract visual features and developed recurrent neural networks for weather property estimation using only image data. Four common weather properties are estimated, i.e., temperature, humidity, visibility, and wind speed. Based on the success of previous works on temperature prediction, we extended them in terms of two aspects. First, by considering the effectiveness of deep multi-task learning, we jointly estimated four weather properties on the basis of the same visual information. Second, we propose that weather property estimations considering temporal evolution can be conducted from two perspectives, i.e., day-wise or hour-wise. A two-dimensional recurrent neural network is thus proposed to unify the two perspectives. In the evaluation, we show that better prediction accuracy can be obtained compared to the state-of-the-art models. We believe that the proposed approach is the first visual weather property estimation model trained based on multi-task learning.
28
Rothlein, David, Joseph DeGutis, and Michael Esterman. "Attentional Fluctuations Influence the Neural Fidelity and Connectivity of Stimulus Representations." Journal of Cognitive Neuroscience 30, no. 9 (2018): 1209–28. http://dx.doi.org/10.1162/jocn_a_01306.
Full textAbstract:
Attention is thought to facilitate both the representation of task-relevant features and the communication of these representations across large-scale brain networks. However, attention is not “all or none,” but rather it fluctuates between stable/accurate (in-the-zone) and variable/error-prone (out-of-the-zone) states. Here we ask how different attentional states relate to the neural processing and transmission of task-relevant information. Specifically, during in-the-zone periods: (1) Do neural representations of task stimuli have greater fidelity? (2) Is there increased communication of this stimulus information across large-scale brain networks? Finally, (3) can the influence of performance-contingent reward be differentiated from zone-based fluctuations? To address these questions, we used fMRI and representational similarity analysis during a visual sustained attention task (the gradCPT). Participants ( n = 16) viewed a series of city or mountain scenes, responding to cities (90% of trials) and withholding to mountains (10%). Representational similarity matrices, reflecting the similarity structure of the city exemplars ( n = 10), were computed from visual, attentional, and default mode networks. Representational fidelity (RF) and representational connectivity (RC) were quantified as the interparticipant reliability of representational similarity matrices within (RF) and across (RC) brain networks. We found that being in the zone was characterized by increased RF in visual networks and increasing RC between visual and attentional networks. Conversely, reward only increased the RC between the attentional and default mode networks. These results diverge with analogous analyses using functional connectivity, suggesting that RC and functional connectivity in tandem better characterize how different mental states modulate the flow of information throughout the brain.
29
Vakhshiteh, Fatemeh, Farshad Almasganj, and Ahmad Nickabadi. "LIP-READING VIA DEEP NEURAL NETWORKS USING HYBRID VISUAL FEATURES." Image Analysis & Stereology 37, no. 2 (2018): 159. http://dx.doi.org/10.5566/ias.1859.
Full textAbstract:
Lip-reading is typically known as visually interpreting the speaker's lip movements during speaking. Experiments over many years have revealed that speech intelligibility increases if visual facial information becomes available. This effect becomes more apparent in noisy environments. Taking steps toward automating this process, some challenges will be raised such as coarticulation phenomenon, visual units' type, features diversity and their inter-speaker dependency. While efforts have been made to overcome these challenges, presentation of a flawless lip-reading system is still under the investigations. This paper searches for a lipreading model with an efficiently developed incorporation and arrangement of processing blocks to extract highly discriminative visual features. Here, application of a properly structured Deep Belief Network (DBN)- based recognizer is highlighted. Multi-speaker (MS) and speaker-independent (SI) tasks are performed over CUAVE database, and phone recognition rates (PRRs) of 77.65% and 73.40% are achieved, respectively. The best word recognition rates (WRRs) achieved in the tasks of MS and SI are 80.25% and 76.91%, respectively. Resulted accuracies demonstrate that the proposed method outperforms the conventional Hidden Markov Model (HMM) and competes well with the state-of-the-art visual speech recognition works.
30
Casabianca, Pietro, and Yu Zhang. "Acoustic-Based UAV Detection Using Late Fusion of Deep Neural Networks." Drones 5, no. 3 (2021): 54. http://dx.doi.org/10.3390/drones5030054.
Full textAbstract:
Multirotor UAVs have become ubiquitous in commercial and public use. As they become more affordable and more available, the associated security risks further increase, especially in relation to airspace breaches and the danger of drone-to-aircraft collisions. Thus, robust systems must be set in place to detect and deal with hostile drones. This paper investigates the use of deep learning methods to detect UAVs using acoustic signals. Deep neural network models are trained with mel-spectrograms as inputs. In this case, Convolutional Neural Networks (CNNs) are shown to be the better performing network, compared with Recurrent Neural Networks (RNNs) and Convolutional Recurrent Neural Networks (CRNNs). Furthermore, late fusion methods have been evaluated using an ensemble of deep neural networks, where the weighted soft voting mechanism has achieved the highest average accuracy of 94.7%, which has outperformed the solo models. In future work, the developed late fusion technique could be utilized with radar and visual methods to further improve the UAV detection performance.
31
Gong, Yan, Georgina Cosma, and Hui Fang. "On the Limitations of Visual-Semantic Embedding Networks for Image-to-Text Information Retrieval." Journal of Imaging 7, no. 8 (2021): 125. http://dx.doi.org/10.3390/jimaging7080125.
Full textAbstract:
Visual-semantic embedding (VSE) networks create joint image–text representations to map images and texts in a shared embedding space to enable various information retrieval-related tasks, such as image–text retrieval, image captioning, and visual question answering. The most recent state-of-the-art VSE-based networks are: VSE++, SCAN, VSRN, and UNITER. This study evaluates the performance of those VSE networks for the task of image-to-text retrieval and identifies and analyses their strengths and limitations to guide future research on the topic. The experimental results on Flickr30K revealed that the pre-trained network, UNITER, achieved 61.5% on average Recall@5 for the task of retrieving all relevant descriptions. The traditional networks, VSRN, SCAN, and VSE++, achieved 50.3%, 47.1%, and 29.4% on average Recall@5, respectively, for the same task. An additional analysis was performed on image–text pairs from the top 25 worst-performing classes using a subset of the Flickr30K-based dataset to identify the limitations of the performance of the best-performing models, VSRN and UNITER. These limitations are discussed from the perspective of image scenes, image objects, image semantics, and basic functions of neural networks. This paper discusses the strengths and limitations of VSE networks to guide further research into the topic of using VSE networks for cross-modal information retrieval tasks.
32
Ni, Xubin, Lirong Yin, Xiaobing Chen, Shan Liu, Bo Yang, and Wenfeng Zheng. "Semantic representation for visual reasoning." MATEC Web of Conferences 277 (2019): 02006. http://dx.doi.org/10.1051/matecconf/201927702006.
Full textAbstract:
In the field of visual reasoning, image features are widely used as the input of neural networks to get answers. However, image features are too redundant to learn accurate characterizations for regular networks. While in human reasoning, abstract description is usually constructed to avoid irrelevant details. Inspired by this, a higher-level representation named semantic representation is introduced in this paper to make visual reasoning more efficient. The idea of the Gram matrix used in the neural style transfer research is transferred here to build a relation matrix which enables the related information between objects to be better represented. The model using semantic representation as input outperforms the same model using image features as input which verifies that more accurate results can be obtained through the introduction of high-level semantic representation in the field of visual reasoning.
33
Vihlman, Mikko, and Arto Visala. "Optical Flow in Deep Visual Tracking." Proceedings of the AAAI Conference on Artificial Intelligence 34, no. 07 (2020): 12112–19. http://dx.doi.org/10.1609/aaai.v34i07.6890.
Full textAbstract:
Single-target tracking of generic objects is a difficult task since a trained tracker is given information present only in the first frame of a video. In recent years, increasingly many trackers have been based on deep neural networks that learn generic features relevant for tracking. This paper argues that deep architectures are often fit to learn implicit representations of optical flow. Optical flow is intuitively useful for tracking, but most deep trackers must learn it implicitly. This paper is among the first to study the role of optical flow in deep visual tracking. The architecture of a typical tracker is modified to reveal the presence of implicit representations of optical flow and to assess the effect of using the flow information more explicitly. The results show that the considered network learns implicitly an effective representation of optical flow. The implicit representation can be replaced by an explicit flow input without a notable effect on performance. Using the implicit and explicit representations at the same time does not improve tracking accuracy. The explicit flow input could allow constructing lighter networks for tracking.
34
Garcia, Noa, Benjamin Renoust, and Yuta Nakashima. "ContextNet: representation and exploration for painting classification and retrieval in context." International Journal of Multimedia Information Retrieval 9, no. 1 (2019): 17–30. http://dx.doi.org/10.1007/s13735-019-00189-4.
Full textAbstract:
AbstractIn automatic art analysis, models that besides the visual elements of an artwork represent the relationships between the different artistic attributes could be very informative. Those kinds of relationships, however, usually appear in a very subtle way, being extremely difficult to detect with standard convolutional neural networks. In this work, we propose to capture contextual artistic information from fine-art paintings with a specific ContextNet network. As context can be obtained from multiple sources, we explore two modalities of ContextNets: one based on multitask learning and another one based on knowledge graphs. Once the contextual information is obtained, we use it to enhance visual representations computed with a neural network. In this way, we are able to (1) capture information about the content and the style with the visual representations and (2) encode relationships between different artistic attributes with the ContextNet. We evaluate our models on both painting classification and retrieval, and by visualising the resulting embeddings on a knowledge graph, we can confirm that our models represent specific stylistic aspects present in the data.
35
Ghariba, Bashir, Mohamed S. Shehata, and Peter McGuire. "Visual Saliency Prediction Based on Deep Learning." Information 10, no. 8 (2019): 257. http://dx.doi.org/10.3390/info10080257.
Full textAbstract:
Human eye movement is one of the most important functions for understanding our surroundings. When a human eye processes a scene, it quickly focuses on dominant parts of the scene, commonly known as a visual saliency detection or visual attention prediction. Recently, neural networks have been used to predict visual saliency. This paper proposes a deep learning encoder-decoder architecture, based on a transfer learning technique, to predict visual saliency. In the proposed model, visual features are extracted through convolutional layers from raw images to predict visual saliency. In addition, the proposed model uses the VGG-16 network for semantic segmentation, which uses a pixel classification layer to predict the categorical label for every pixel in an input image. The proposed model is applied to several datasets, including TORONTO, MIT300, MIT1003, and DUT-OMRON, to illustrate its efficiency. The results of the proposed model are quantitatively and qualitatively compared to classic and state-of-the-art deep learning models. Using the proposed deep learning model, a global accuracy of up to 96.22% is achieved for the prediction of visual saliency.
36
Kalinina, M. O., and P. L. Nikolaev. "Book spine recognition with the use of deep neural networks." Computer Optics 44, no. 6 (2020): 968–77. http://dx.doi.org/10.18287/2412-6179-co-731.
Full textAbstract:
Nowadays deep neural networks play a significant part in various fields of human activity. Especially they benefit spheres dealing with large amounts of data and lengthy operations on obtaining and processing information from the visual environment. This article deals with the development of a convolutional neural network based on the YOLO architecture, intended for real-time book recognition. The creation of an original data set and the training of the deep neural network are described. The structure of the neural network obtained is presented and the most frequently used metrics for estimating the quality of the network performance are considered. A brief review of the existing types of neural network architectures is also made. YOLO architecture possesses a number of advantages that allow it to successfully compete with other models and make it the most suitable variant for creating an object detection network since it enables some of the common disadvantages of such networks to be significantly mitigated (such as recognition of similarly looking, same-color book coves or slanted books). The results obtained in the course of training the deep neural network allow us to use it as a basis for the development of the software for book spine recognition.
37
Gulshad, Sadaf, and Arnold Smeulders. "Counterfactual attribute-based visual explanations for classification." International Journal of Multimedia Information Retrieval 10, no. 2 (2021): 127–40. http://dx.doi.org/10.1007/s13735-021-00208-3.
Full textAbstract:
AbstractIn this paper, our aim is to provide human understandable intuitive factual and counterfactual explanations for the decisions of neural networks. Humans tend to reinforce their decisions by providing attributes and counterattributes. Hence, in this work, we utilize attributes as well as examples to provide explanations. In order to provide counterexplanations we make use of directed perturbations to arrive at the counterclass attribute values in doing so, we explain what is present and what is absent in the original image. We evaluate our method when images are misclassified into closer counterclasses as well as when misclassified into completely different counterclasses. We conducted experiments on both finegrained as well as coarsegrained datasets. We verified our attribute-based explanations method both quantitatively and qualitatively and showed that attributes provide discriminating and human understandable explanations for both standard as well as robust networks.
38
Ergun, Hilal, Yusuf Caglar Akyuz, Mustafa Sert, and Jianquan Liu. "Early and Late Level Fusion of Deep Convolutional Neural Networks for Visual Concept Recognition." International Journal of Semantic Computing 10, no. 03 (2016): 379–97. http://dx.doi.org/10.1142/s1793351x16400158.
Full textAbstract:
Visual concept recognition is an active research field in the last decade. Related to this attention, deep learning architectures are showing great promise in various computer vision domains including image classification, object detection, event detection and action recognition in videos. In this study, we investigate various aspects of convolutional neural networks for visual concept recognition. We analyze recent studies and different network architectures both in terms of running time and accuracy. In our proposed visual concept recognition system, we first discuss various important properties of popular convolutional network architecture under consideration. Then we describe our method for feature extraction at different levels of abstraction. We present extensive empirical information along with best practices for big data practitioners. Using these best practices we propose efficient fusion mechanisms both for single and multiple network models. We present state-of-the-art results on benchmark datasets while keeping computational costs at low level. Our results show that these state-of-the-art results can be reached without using extensive data augmentation techniques.
39
White, Robert L., and Lawrence H. Snyder. "Spatial constancy and the brain: insights from neural networks." Philosophical Transactions of the Royal Society B: Biological Sciences 362, no. 1479 (2007): 375–82. http://dx.doi.org/10.1098/rstb.2006.1965.
Full textAbstract:
To form an accurate internal representation of visual space, the brain must accurately account for movements of the eyes, head or body. Updating of internal representations in response to these movements is especially important when remembering spatial information, such as the location of an object, since the brain must rely on non-visual extra-retinal signals to compensate for self-generated movements. We investigated the computations underlying spatial updating by constructing a recurrent neural network model to store and update a spatial location based on a gaze shift signal, and to do so flexibly based on a contextual cue. We observed a striking similarity between the patterns of behaviour produced by the model and monkeys trained to perform the same task, as well as between the hidden units of the model and neurons in the lateral intraparietal area (LIP). In this report, we describe the similarities between the model and single unit physiology to illustrate the usefulness of neural networks as a tool for understanding specific computations performed by the brain.
40
Orbán, Levente L., and Sylvain Chartier. "Unsupervised Neural Network Quantifies the Cost of Visual Information Processing." PLOS ONE 10, no. 7 (2015): e0132218. http://dx.doi.org/10.1371/journal.pone.0132218.
Full text
41
Michaels, Jonathan A., Stefan Schaffelhofer, Andres Agudelo-Toro, and Hansjörg Scherberger. "A goal-driven modular neural network predicts parietofrontal neural dynamics during grasping." Proceedings of the National Academy of Sciences 117, no. 50 (2020): 32124–35. http://dx.doi.org/10.1073/pnas.2005087117.
Full textAbstract:
One of the primary ways we interact with the world is using our hands. In macaques, the circuit spanning the anterior intraparietal area, the hand area of the ventral premotor cortex, and the primary motor cortex is necessary for transforming visual information into grasping movements. However, no comprehensive model exists that links all steps of processing from vision to action. We hypothesized that a recurrent neural network mimicking the modular structure of the anatomical circuit and trained to use visual features of objects to generate the required muscle dynamics used by primates to grasp objects would give insight into the computations of the grasping circuit. Internal activity of modular networks trained with these constraints strongly resembled neural activity recorded from the grasping circuit during grasping and paralleled the similarities between brain regions. Network activity during the different phases of the task could be explained by linear dynamics for maintaining a distributed movement plan across the network in the absence of visual stimulus and then generating the required muscle kinematics based on these initial conditions in a module-specific way. These modular models also outperformed alternative models at explaining neural data, despite the absence of neural data during training, suggesting that the inputs, outputs, and architectural constraints imposed were sufficient for recapitulating processing in the grasping circuit. Finally, targeted lesioning of modules produced deficits similar to those observed in lesion studies of the grasping circuit, providing a potential model for how brain regions may coordinate during the visually guided grasping of objects.
42
Brunel, Nicolas. "Hebbian Learning of Context in Recurrent Neural Networks." Neural Computation 8, no. 8 (1996): 1677–710. http://dx.doi.org/10.1162/neco.1996.8.8.1677.
Full textAbstract:
Single electrode recordings in the inferotemporal cortex of monkeys during delayed visual memory tasks provide evidence for attractor dynamics in the observed region. The persistent elevated delay activities could be internal representations of features of the learned visual stimuli shown to the monkey during training. When uncorrelated stimuli are presented during training in a fixed sequence, these experiments display significant correlations between the internal representations. Recently a simple model of attractor neural network has reproduced quantitatively the measured correlations. An underlying assumption of the model is that the synaptic matrix formed during the training phase contains in its efficacies information about the contiguity of persistent stimuli in the training sequence. We present here a simple unsupervised learning dynamics that produces such a synaptic matrix if sequences of stimuli are repeatedly presented to the network at fixed order. The resulting matrix is then shown to convert temporal correlations during training into spatial correlations between attractors. The scenario is that, in the presence of selective delay activity, at the presentation of each stimulus, the activity distribution in the neural assembly contains information of both the current stimulus and the previous one (carried by the attractor). Thus the recurrent synaptic matrix can code not only for each of the stimuli presented to the network but also for their context. We combine the idea that for learning to be effective, synaptic modification should be stochastic, with the fact that attractors provide learnable information about two consecutive stimuli. We calculate explicitly the probability distribution of synaptic efficacies as a function of training protocol, that is, the order in which stimuli are presented to the network. We then solve for the dynamics of a network composed of integrate-and-fire excitatory and inhibitory neurons with a matrix of synaptic collaterals resulting from the learning dynamics. The network has a stable spontaneous activity, and stable delay activity develops after a critical learning stage. The availability of a learning dynamics makes possible a number of experimental predictions for the dependence of the delay activity distributions and the correlations between them, on the learning stage and the learning protocol. In particular it makes specific predictions for pair-associates delay experiments.
43
Wang, Yong, Xinbin Luo, Lu Ding, Shan Fu, and Xian Wei. "Detection based visual tracking with convolutional neural network." Knowledge-Based Systems 175 (July 2019): 62–71. http://dx.doi.org/10.1016/j.knosys.2019.03.012.
Full text
44
Liu, Yu, Xun Chen, Juan Cheng, Hu Peng, and Zengfu Wang. "Infrared and visible image fusion with convolutional neural networks." International Journal of Wavelets, Multiresolution and Information Processing 16, no. 03 (2018): 1850018. http://dx.doi.org/10.1142/s0219691318500182.
Full textAbstract:
The fusion of infrared and visible images of the same scene aims to generate a composite image which can provide a more comprehensive description of the scene. In this paper, we propose an infrared and visible image fusion method based on convolutional neural networks (CNNs). In particular, a siamese convolutional network is applied to obtain a weight map which integrates the pixel activity information from two source images. This CNN-based approach can deal with two vital issues in image fusion as a whole, namely, activity level measurement and weight assignment. Considering the different imaging modalities of infrared and visible images, the merging procedure is conducted in a multi-scale manner via image pyramids and a local similarity-based strategy is adopted to adaptively adjust the fusion mode for the decomposed coefficients. Experimental results demonstrate that the proposed method can achieve state-of-the-art results in terms of both visual quality and objective assessment.
45
Mei, Xiaoguang, Erting Pan, Yong Ma, et al. "Spectral-Spatial Attention Networks for Hyperspectral Image Classification." Remote Sensing 11, no. 8 (2019): 963. http://dx.doi.org/10.3390/rs11080963.
Full textAbstract:
Many deep learning models, such as convolutional neural network (CNN) and recurrent neural network (RNN), have been successfully applied to extracting deep features for hyperspectral tasks. Hyperspectral image classification allows distinguishing the characterization of land covers by utilizing their abundant information. Motivated by the attention mechanism of the human visual system, in this study, we propose a spectral-spatial attention network for hyperspectral image classification. In our method, RNN with attention can learn inner spectral correlations within a continuous spectrum, while CNN with attention is designed to focus on saliency features and spatial relevance between neighboring pixels in the spatial dimension. Experimental results demonstrate that our method can fully utilize the spectral and spatial information to obtain competitive performance.
46
YUE, TAI-WEN, and SUCHEN CHIANG. "A NEURAL-NETWORK APPROACH FOR VISUAL CRYPTOGRAPHY AND AUTHORIZATION." International Journal of Neural Systems 14, no. 03 (2004): 175–87. http://dx.doi.org/10.1142/s012906570400198x.
Full textAbstract:
In this paper, we propose a neural-network approach for visual authorization, which is an application of visual cryptography (VC). The scheme contains a key-share and a set of user-shares. The administrator owns the key-share, and each user owns a user-share issued by the administrator from the user-share set. The shares in the user-share set are visually indistinguishable, i.e. they have the same pictorial meaning. However, the stacking of the key-share with different user-shares will reveal significantly different images. Therefore, the administrator (in fact, only the administrator) can visually recognize the authority assigned to a particular user by viewing the information appearing in the superposed image of key-share and user-share. This approach is completely different from traditional VC approaches. The salient features include: (i) the access schemes are described using a set of graytone images, and (ii) the codebooks to fulfil them are not required; and (iii) the size of share images is the same as the size of target image.
47
Koji, Yukichi, Naoyoshi Takatsu, and Masanari Oh. "Visual solder inspection using neural network." Systems and Computers in Japan 27, no. 1 (1996): 92–100. http://dx.doi.org/10.1002/scj.4690270109.
Full text
48
Seeliger, K., L. Ambrogioni, Y. Güçlütürk, L. M. van den Bulk, U. Güçlü, and M. A. J. van Gerven. "End-to-end neural system identification with neural information flow." PLOS Computational Biology 17, no. 2 (2021): e1008558. http://dx.doi.org/10.1371/journal.pcbi.1008558.
Full textAbstract:
Neural information flow (NIF) provides a novel approach for system identification in neuroscience. It models the neural computations in multiple brain regions and can be trained end-to-end via stochastic gradient descent from noninvasive data. NIF models represent neural information processing via a network of coupled tensors, each encoding the representation of the sensory input contained in a brain region. The elements of these tensors can be interpreted as cortical columns whose activity encodes the presence of a specific feature in a spatiotemporal location. Each tensor is coupled to the measured data specific to a brain region via low-rank observation models that can be decomposed into the spatial, temporal and feature receptive fields of a localized neuronal population. Both these observation models and the convolutional weights defining the information processing within regions are learned end-to-end by predicting the neural signal during sensory stimulation. We trained a NIF model on the activity of early visual areas using a large-scale fMRI dataset recorded in a single participant. We show that we can recover plausible visual representations and population receptive fields that are consistent with empirical findings.
49
Ramsey, Richard. "Neural Integration in Body Perception." Journal of Cognitive Neuroscience 30, no. 10 (2018): 1442–51. http://dx.doi.org/10.1162/jocn_a_01299.
Full textAbstract:
The perception of other people is instrumental in guiding social interactions. For example, the appearance of the human body cues a wide range of inferences regarding sex, age, health, and personality, as well as emotional state and intentions, which influence social behavior. To date, most neuroscience research on body perception has aimed to characterize the functional contribution of segregated patches of cortex in the ventral visual stream. In light of the growing prominence of network architectures in neuroscience, the current article reviews neuroimaging studies that measure functional integration between different brain regions during body perception. The review demonstrates that body perception is not restricted to processing in the ventral visual stream but instead reflects a functional alliance between the ventral visual stream and extended neural systems associated with action perception, executive functions, and theory of mind. Overall, these findings demonstrate how body percepts are constructed through interactions in distributed brain networks and underscore that functional segregation and integration should be considered together when formulating neurocognitive theories of body perception. Insight from such an updated model of body perception generalizes to inform the organizational structure of social perception and cognition more generally and also informs disorders of body image, such as anorexia nervosa, which may rely on atypical integration of body-related information.
50
Tai, Lei, Shaohua Li, and Ming Liu. "Autonomous exploration of mobile robots through deep neural networks." International Journal of Advanced Robotic Systems 14, no. 4 (2017): 172988141770357. http://dx.doi.org/10.1177/1729881417703571.
Full textAbstract:
The exploration problem of mobile robots aims to allow mobile robots to explore an unknown environment. We describe an indoor exploration algorithm for mobile robots using a hierarchical structure that fuses several convolutional neural network layers with decision-making process. The whole system is trained end to end by taking only visual information (RGB-D information) as input and generates a sequence of main moving direction as output so that the robot achieves autonomous exploration ability. The robot is a TurtleBot with a Kinect mounted on it. The model is trained and tested in a real world environment. And the training data set is provided for download. The outputs of the test data are compared with the human decision. We use Gaussian process latent variable model to visualize the feature map of last convolutional layer, which proves the effectiveness of this deep convolution neural network mode. We also present a novel and lightweight deep-learning library libcnn especially for deep-learning processing of robotics tasks.