Relevant bibliographies by topics / Deep Distance Learning

Academic literature on the topic 'Deep Distance Learning'

Author: Grafiati
Published: 18 August 2021
Last updated: 1 February 2022

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

Select a source type:

Consult the lists of relevant articles, books, theses, conference reports, and other scholarly sources on the topic 'Deep Distance Learning.'

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.

Contents

  1. Journal articles
  2. Dissertations / Theses
  3. Books
  4. Book chapters
  5. Conference papers

Journal articles on the topic "Deep Distance Learning":

1

Roostaiyan, Seyed Mahdi, Ehsan Imani, and Mahdieh Soleymani Baghshah. "Multi-modal deep distance metric learning." Intelligent Data Analysis 21, no. 6 (November 15, 2017): 1351–69. http://dx.doi.org/10.3233/ida-163196.

Full text
APA, Harvard, Vancouver, ISO, and other styles
2

Kusumalatha, Ms K. "Social Distancing Detection using Deep Learning." International Journal for Research in Applied Science and Engineering Technology 9, no. VI (June 30, 2021): 3284–92. http://dx.doi.org/10.22214/ijraset.2021.35335.

Full text
APA, Harvard, Vancouver, ISO, and other styles
Abstract:
The continuous COVID-19 Covid episode has caused a worldwide calamity with its dangerous spreading. due to the shortfall of successful healing specialists and therefore the lack of vaccinations against the infection, populace weakness increments. within the current circumstance, as there aren't any antibodies accessible; hence, social removing is believed to be a sufficient precautionary measure (standard) against the spread of the pandemic infection. the risks of infection spread may be limited by keeping aloof from actual contact among individuals. the rationale for this work is, thusly, to administer a profound learning stage to social distance is additionally executed to create the exactness of the model. Thusly, the popularity calculation utilizes a pre-prepared calculation that's related to an additional prepared the distinguished jumping box centroid's pairwise distances of people are resolved. To appraise social distance infringement between individuals, we utilized an estimation of actual distance to pixel and set a grip. An infringement limit is ready up to assess whether the space esteem breaks the bottom social distance edge. Analyses are done on various video arrangements to check the proficiency of the model. Discoveries show that the created system effectively recognizes folks that walk excessively close and penetrates/abuses social seperation; also, the trade collecting approach upholds the general efficiency of the model. The precision of 91% and 96% achieved by the acknowledgment model without and with move learning, independently. The accompanying precision of the model is 94%
3

Utkin, Lev V., and Mikhail A. Ryabinin. "Discriminative Metric Learning with Deep Forest." International Journal on Artificial Intelligence Tools 28, no. 02 (March 2019): 1950007. http://dx.doi.org/10.1142/s0218213019500076.

Full text
APA, Harvard, Vancouver, ISO, and other styles
Abstract:
A Discriminative Deep Forest (DisDF) as a metric learning algorithm is proposed in the paper. It is based on the Deep Forest or gcForest proposed by Zhou and Feng and can be viewed as a gcForest modification. The case of the fully supervised learning is studied when the class labels of individual training examples are known. The main idea underlying the algorithm is to assign weights to decision trees in random forest in order to reduce distances between objects from the same class and to increase them between objects from different classes. The weights are training parameters. A specific objective function which combines Euclidean and Manhattan distances and simplifies the optimization problem for training the DisDF is proposed. The numerical experiments illustrate the proposed distance metric algorithm.
4

Gao, Wei, Yaojun Chen, Abdul Qudair Baig, and Yunqing Zhang. "Ontology geometry distance computation using deep learning technology." Journal of Intelligent & Fuzzy Systems 35, no. 4 (October 27, 2018): 4517–24. http://dx.doi.org/10.3233/jifs-169770.

Full text
APA, Harvard, Vancouver, ISO, and other styles
5

Xu, Jinbo. "Distance-based protein folding powered by deep learning." Proceedings of the National Academy of Sciences 116, no. 34 (August 9, 2019): 16856–65. http://dx.doi.org/10.1073/pnas.1821309116.

Full text
APA, Harvard, Vancouver, ISO, and other styles
Abstract:
Direct coupling analysis (DCA) for protein folding has made very good progress, but it is not effective for proteins that lack many sequence homologs, even coupled with time-consuming conformation sampling with fragments. We show that we can accurately predict interresidue distance distribution of a protein by deep learning, even for proteins with ∼60 sequence homologs. Using only the geometric constraints given by the resulting distance matrix we may construct 3D models without involving extensive conformation sampling. Our method successfully folded 21 of the 37 CASP12 hard targets with a median family size of 58 effective sequence homologs within 4 h on a Linux computer of 20 central processing units. In contrast, DCA-predicted contacts cannot be used to fold any of these hard targets in the absence of extensive conformation sampling, and the best CASP12 group folded only 11 of them by integrating DCA-predicted contacts into fragment-based conformation sampling. Rigorous experimental validation in CASP13 shows that our distance-based folding server successfully folded 17 of 32 hard targets (with a median family size of 36 sequence homologs) and obtained 70% precision on the top L/5 long-range predicted contacts. The latest experimental validation in CAMEO shows that our server predicted correct folds for 2 membrane proteins while all of the other servers failed. These results demonstrate that it is now feasible to predict correct fold for many more proteins lack of similar structures in the Protein Data Bank even on a personal computer.
6

Yiwere, Mariam, and Eun Joo Rhee. "Sound Source Distance Estimation Using Deep Learning: An Image Classification Approach." Sensors 20, no. 1 (December 27, 2019): 172. http://dx.doi.org/10.3390/s20010172.

Full text
APA, Harvard, Vancouver, ISO, and other styles
Abstract:
This paper presents a sound source distance estimation (SSDE) method using a convolutional recurrent neural network (CRNN). We approach the sound source distance estimation task as an image classification problem, and we aim to classify a given audio signal into one of three predefined distance classes—one meter, two meters, and three meters—irrespective of its orientation angle. For the purpose of training, we create a dataset by recording audio signals at the three different distances and three angles in different rooms. The CRNN is trained using time-frequency representations of the audio signals. Specifically, we transform the audio signals into log-scaled mel spectrograms, allowing the convolutional layers to extract the appropriate features required for the classification. When trained and tested with combined datasets from all rooms, the proposed model exhibits high classification accuracies; however, training and testing the model in separate rooms results in lower accuracies, indicating that further study is required to improve the method’s generalization ability. Our experimental results demonstrate that it is possible to estimate sound source distances in known environments by classification using the log-scaled mel spectrogram.
7

Liu, Jian, and Liming Feng. "Diversity Evolutionary Policy Deep Reinforcement Learning." Computational Intelligence and Neuroscience 2021 (August 3, 2021): 1–11. http://dx.doi.org/10.1155/2021/5300189.

Full text
APA, Harvard, Vancouver, ISO, and other styles
Abstract:
The reinforcement learning algorithms based on policy gradient may fall into local optimal due to gradient disappearance during the update process, which in turn affects the exploration ability of the reinforcement learning agent. In order to solve the above problem, in this paper, the cross-entropy method (CEM) in evolution policy, maximum mean difference (MMD), and twin delayed deep deterministic policy gradient algorithm (TD3) are combined to propose a diversity evolutionary policy deep reinforcement learning (DEPRL) algorithm. By using the maximum mean discrepancy as a measure of the distance between different policies, some of the policies in the population maximize the distance between them and the previous generation of policies while maximizing the cumulative return during the gradient update. Furthermore, combining the cumulative returns and the distance between policies as the fitness of the population encourages more diversity in the offspring policies, which in turn can reduce the risk of falling into local optimal due to the disappearance of the gradient. The results in the MuJoCo test environment show that DEPRL has achieved excellent performance on continuous control tasks; especially in the Ant-v2 environment, the return of DEPRL ultimately achieved a nearly 20% improvement compared to TD3.
8

Chetouani, Aladine, and Marius Pedersen. "Image Quality Assessment without Reference by Combining Deep Learning-Based Features and Viewing Distance." Applied Sciences 11, no. 10 (May 19, 2021): 4661. http://dx.doi.org/10.3390/app11104661.

Full text
APA, Harvard, Vancouver, ISO, and other styles
Abstract:
An abundance of objective image quality metrics have been introduced in the literature. One important essential aspect that perceived image quality is dependent on is the viewing distance from the observer to the image. We introduce in this study a novel image quality metric able to estimate the quality of a given image without reference for different viewing distances between the image and the observer. We first select relevant patches from the image using saliency information. For each patch, a feature vector is extracted from a convolutional neural network model and concatenated at the viewing distance, for which the quality is predicted. The resulting vector is fed to fully connected layers to predict subjective scores for the considered viewing distance. The proposed method was evaluated using the Colourlab Image Database: Image Quality and Viewing Distance-changed Image Database. Both databases provide subjective scores at two different viewing distances. In the Colourlab Image Database: Image Quality we obtain a Pearson correlation of 0.87 at both 50 cm and 100 cm viewing distances, while in the Viewing Distance-changed Image Database we obtained a Pearson correlation of 0.93 and 0.94 at viewing distance of four and six times the image height. The results show the efficiency of our method and its generalization ability.
9

Ma, Guixiang, Nesreen K. Ahmed, Theodore L. Willke, and Philip S. Yu. "Deep graph similarity learning: a survey." Data Mining and Knowledge Discovery 35, no. 3 (March 24, 2021): 688–725. http://dx.doi.org/10.1007/s10618-020-00733-5.

Full text
APA, Harvard, Vancouver, ISO, and other styles
Abstract:
AbstractIn many domains where data are represented as graphs, learning a similarity metric among graphs is considered a key problem, which can further facilitate various learning tasks, such as classification, clustering, and similarity search. Recently, there has been an increasing interest in deep graph similarity learning, where the key idea is to learn a deep learning model that maps input graphs to a target space such that the distance in the target space approximates the structural distance in the input space. Here, we provide a comprehensive review of the existing literature of deep graph similarity learning. We propose a systematic taxonomy for the methods and applications. Finally, we discuss the challenges and future directions for this problem.
10

Kaya and Bilge. "Deep Metric Learning: A Survey." Symmetry 11, no. 9 (August 21, 2019): 1066. http://dx.doi.org/10.3390/sym11091066.

Full text
APA, Harvard, Vancouver, ISO, and other styles
Abstract:
Metric learning aims to measure the similarity among samples while using an optimal distance metric for learning tasks. Metric learning methods, which generally use a linear projection, are limited in solving real-world problems demonstrating non-linear characteristics. Kernel approaches are utilized in metric learning to address this problem. In recent years, deep metric learning, which provides a better solution for nonlinear data through activation functions, has attracted researchers' attention in many different areas. This article aims to reveal the importance of deep metric learning and the problems dealt with in this field in the light of recent studies. As far as the research conducted in this field are concerned, most existing studies that are inspired by Siamese and Triplet networks are commonly used to correlate among samples while using shared weights in deep metric learning. The success of these networks is based on their capacity to understand the similarity relationship among samples. Moreover, sampling strategy, appropriate distance metric, and the structure of the network are the challenging factors for researchers to improve the performance of the network model. This article is considered to be important, as it is the first comprehensive study in which these factors are systematically analyzed and evaluated as a whole and supported by comparing the quantitative results of the methods.
More sources
You might also be interested in the extended bibliographies on the topic 'Deep Distance Learning' for particular source types:
Journal articles Dissertations / Theses

Dissertations / Theses on the topic "Deep Distance Learning":

1

Runow, Björn. "Deep Learning for Point Detection in Images." Thesis, Linköpings universitet, Datorseende, 2020. http://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-166644.

Full text
APA, Harvard, Vancouver, ISO, and other styles
Abstract:
The main result of this thesis is a deep learning model named BearNet, which can be trained to detect an arbitrary amount of objects as a set of points. The model is trained using the Weighted Hausdorff distance as loss function. BearNet has been applied and tested on two problems from the industry. These are: From an intensity image, detect two pocket points of an EU-pallet which an autonomous forklift could utilize when determining where to insert its forks. From a depth image, detect the start, bend and end points of a straw attached to a juice package, in order to help determine if the straw has been attached correctly. In the development process of BearNet I took inspiration from the designs of U-Net, UNet++ and a high resolution network named HRNet. Further, I used a dataset containing RGB-images from a surveillance camera located inside a mall, on which the aim was to detect head positions of all pedestrians. In an attempt to reproduce a result from another study, I found that the mall dataset suffers from training set contamination when a model is trained, validated, and tested on it with random sampling. Hence, I propose that the mall dataset is evaluated with a sequential data split strategy, to limit the problem. I found that the BearNet architecture is well suited for both the EU-pallet and straw datasets, and that it can be successfully used on either RGB,  intensity or depth images. On the EU-pallet and straw datasets, BearNet consistently produces point estimates within five and six pixels of ground truth, respectively. I also show that the straw dataset only constitutes a small subset of all the challenges that exist in the problem domain related to the attachment of a straw to a juice package, and that one therefore cannot train a robust deep learning model on it. As an example of this, models trained on the straw dataset cannot correctly handle samples in which there is no straw visible.
2

Gao, Shuting. "Learner support for distance learners : A study of six cases of ICT-based distance education institutions in China." Doctoral thesis, Stockholms universitet, Institutionen för pedagogik och didaktik, 2012. http://urn.kb.se/resolve?urn=urn:nbn:se:su:diva-82487.

Full text
APA, Harvard, Vancouver, ISO, and other styles
Abstract:
This thesis focuses on learner support in Chinese distance education. It draws a picture of Chinese modern distance education, covering the major issues in the field of learner support, and small group work as peer support. The aim of the study is to find out whether or not the learner support, that distance students at university level obtained, has the tendency to support students’ deep learning. The aim has been achieved by examining learner support in six institutions of ICT-based distance education in China. Three other sources of learner support are investigated. The main objectives of the study are: 1) to describe the distance students’ characteristics; 2) to examine their learning habits, learning organizations, and their interactions; 3) to investigate the student support provided by the institutions; family support; societal support; and peer support in the form of small group work. The purpose of this study is to define current practices of learner support in the six distance education institutions, determining the extent of similarities and differences on learner support services among these institutions. The study is applying a case-study approach, using qualitative and quantitative methods to investigate the six Chinese distance education institutions. During the first stage, several field visits were conducted in different research sites with on-site participant observation, non-participant observation and interviews for obtaining knowledge of Chinese distance education. In the second stage, a survey with a student questionnaire was distributed to students present and others online, in total 587. In addition, semi-structured interviews with staff members (administrators, instructors and tutors), individual students, and student focus groups were performed. The present research is one of the few in-depth case studies that focus on the relation between learner support system and different approaches to learning. On the basis of these research findings, the importance of a well-designed learner support system for the distance learner, a system for fostering creative, critical or independent thinking skills, or deep learning, in line with Chinese cultural and social conditions, is underlined.
3

Bartoli, Simone. "Deploying deep learning for 3D reconstruction from monocular video sequences." Master's thesis, Alma Mater Studiorum - Università di Bologna, 2021. http://amslaurea.unibo.it/22402/.

Full text
APA, Harvard, Vancouver, ISO, and other styles
Abstract:
3D reconstruction from monocular video sequences is a field of increasingly interest in the late years. Before the growth of deep learning, the retrieve of depth information from single images was possible only with RGBD sensors or algorithmic approaches. However, the availability of more and more data has allowed the training of monocular depth estimation neural networks, introducing innovative data-driven techniques. Since recovering ground-truth labels for depth estimation is very challenging, most of the research has focused on unsupervised or semi-supervised training approaches. The currently state of the art for 3D reconstruction is defined by an algorithmic method which exploits a Structure from Motion and Multi-View Stereo pipeline. Nevertheless, the whole approach is based on keypoints extraction, which provides well-known limitations when it comes to texture-less, reflective and/or transparent surfaces. Consequentely, a possible way to predict dense depth maps even in absence of keypoints is by employing neural networks. This work proposes a novel data-driven pipeline for 3D reconstruction from monocular video sequences. It exploits a fine-tuning technique to adjust the weights of a pre-trained depth estimation neural network depending on the input scene. In doing so, the network can learn the features of a particular object and can provide semi real-time depth predictions for 3D reconstruction. Furthermore, the project provides a comparison with a custom implementation of the current state of the art approach and shows the potential of this innovative data-driven pipeline.
4

Kuhad, Pallavi. "A Deep Learning and Auto-Calibration Approach for Food Recognition and Calorie Estimation in Mobile e-Health." Thesis, Université d'Ottawa / University of Ottawa, 2015. http://hdl.handle.net/10393/32455.

Full text
APA, Harvard, Vancouver, ISO, and other styles
Abstract:
High calorie intake has proved harmful worldwide, as it has led to many diseases. However, dieticians have deemed that a standard intake of number of calories is essential to maintain the right balance of calorie content in human body. In this thesis, we consider the category of tools that use image processing to recognize single and multiple mixed-food objects, namely Deep Learning and the Support Vector Machine (SVM). We propose a method for the fully automatic and user-friendly calibration of the sizes of food portions. This calibration is required to estimate the total number of calories in food portions. In this work, to compute the number of calories in the food object, we go beyond the finger-based calorie calibration method that has been used in the past, by automatically measuring the distance between the user and the food object. We implement a block resize method that uses the measured distance values along with the recognized food object name to further estimate calories. While measuring distance, the system also assists the user in real time to capture an image that enables the quick and accurate calculation of the number of calories in the food object. The experimental results showed that our method, which uses deep learning to analyze food objects, led to an improvement of 16.58% in terms of recognition, over the SVM-based method. Moreover, the block resize method showed that percentage error for calorie estimation was reduced to 3.64% as compared to 5% achieved in previous methods.
5

Ravaglia, Daniele. "Performance dei Variational Autoencoders in relazione al training set." Bachelor's thesis, Alma Mater Studiorum - Università di Bologna, 2019. http://amslaurea.unibo.it/19603/.

Full text
APA, Harvard, Vancouver, ISO, and other styles
Abstract:
Questa tesi tratta di modelli generativi in ambito di deep learning e delle metriche utilizzate per valutarli. In particolare si analizza la Frechét Inception Distance (FID), il funzionamento dei Variational Autoencoders (VAE) e le diverse strategie che si possono adottare per comporre il training set per migliorare le performance di questi ultimi in fase generativa. Vengono inoltre trattate l'adozione di un'architettura a due livelli e la stima ex-post della distribuzione dello spazio latente. Viene altresì condotto uno studio sul comportamento della FID in base al dataset usato, e in particolare dataset composti da immagini ripetute progressivamente e dataset contenenti immagini scomposte in varie sezioni e ricomposte casualmente. Unitamente allo studio sopracitato si prova a selezionare il dataset secondo due criteri. Il primo criterio, l'errore di ricostruzione, permette di selezionare le immagini sulle quali il VAE ha meno difficoltà in fase di ricostruzione. Il secondo criterio, la distanza di Mahalanobis, permette di calcolare quanto un'immagine sia rappresentativa dell'insieme delle immagini usate per calcolare la FID. In conclusione, i risultati ottenuti vengono presentati e confrontati con i risultati in bibliografia.
6

Trentin, Matteo. "Estensione a due stadi di modelli VAE per la generazione di immagini." Bachelor's thesis, Alma Mater Studiorum - Università di Bologna, 2019. http://amslaurea.unibo.it/19138/.

Full text
APA, Harvard, Vancouver, ISO, and other styles
Abstract:
Una particolare applicazione delle tecniche di deep learning riguarda la generazione di nuovi contenuti, come ad esempio audio o immagini; un approccio popolare a questo campo consiste nei Variational Autoencoder, o VAE. In questa tesi vengono inizialmente presentati alcuni concetti base di deep learning e spiegato il funzionamento dei VAE; successivamente viene analizzato un miglioramento recentemente proposto in letteratura a questo tipo di modello, il Two-Stage VAE, e ne vengono verificati i vantaggi dal punto di vista della qualità generativa; viene poi mostrata una possibile e originale estensione condizionale al Two-Stage VAE, con relativi risultati sperimentali su due diversi dataset.
7

Trenholm, Sven. "Adaptation of tertiary mathematics instruction to the virtual medium : approaches to assessment practice." Thesis, Loughborough University, 2013. https://dspace.lboro.ac.uk/2134/12561.

Full text
APA, Harvard, Vancouver, ISO, and other styles
Abstract:
Mathematics has been singled out as a challenging discipline to teach fully online (FO). Yet both the demand for and development of FO mathematics courses is increasing with little known about the quality of these courses and many calling for research. Whereas most research has investigated the nature of these courses by examining instructional outputs such as student grades this research seeks the same insight but by examining instructional inputs. Specifically, it seeks to investigate the nature of current assessment practice in FO mathematics courses. To conduct this investigation, deep learning (Marton & S??lj??, 1976a, 1976b) is used as the principle theoretical framework. From the growing body of literature associated with deep learning, two studies are selected to investigate current FO mathematics instructors assessment practices. An additional framework based on empirical findings related to the use of different kinds of feedback is also used. In total, six study measures are used to conduct a mixed methods study in two parts. The target demographic and course context are tertiary instructors from Western nations that teach introductory level mathematics (particularly statistics and calculus). The first study explores current FO mathematics assessment practices using an online survey (n=70) where the majority of participants originate from US higher education institutions. In the second study six of the US survey participants are interviewed about how their assessment practices and approaches used in their FO mathematics courses differ from those used in their face-to-face (F2F) mathematics courses. This study represents the first known attempt to investigate the nature of tertiary FO mathematics instructors assessment practices using appropriate theoretical frameworks. In particular, it investigates mathematics instructors experiences of the affordances and constraints of the FO course context when adapting their F2F practice to this new environment. Findings suggest the FO course context is a challenging environment for instructors to orient their teaching and assessment practice in a way that helps develop students understanding of mathematics. Analysis of interview responses suggests the problem lies with the nature of interactivity provided in the FO course context.
8

Carbonera, Luvizon Diogo. "Apprentissage automatique pour la reconnaissance d'action humaine et l'estimation de pose à partir de l'information 3D." Thesis, Cergy-Pontoise, 2019. http://www.theses.fr/2019CERG1015.

Full text
APA, Harvard, Vancouver, ISO, and other styles
Abstract:
La reconnaissance d'actions humaines en 3D est une tâche difficile en raisonde la complexité de mouvements humains et de la variété des poses et desactions accomplies par différents sujets. Les technologies récentes baséessur des capteurs de profondeur peuvent fournir les représentationssquelettiques à faible coût de calcul, ce qui est une information utilepour la reconnaissance d'actions.Cependant, ce type de capteurs se limite à des environnementscontrôlés et génère fréquemment des données bruitées. Parallèlement à cesavancées technologiques, les réseaux de neurones convolutifs (CNN) ontmontré des améliorations significatives pour la reconnaissance d’actions etpour l’estimation de la pose humaine en 3D à partir des images couleurs.Même si ces problèmes sont étroitement liés, les deux tâches sont souventtraitées séparément dans la littérature.Dans ce travail, nous analysons le problème de la reconnaissance d'actionshumaines dans deux scénarios: premièrement, nous explorons lescaractéristiques spatiales et temporelles à partir de représentations desquelettes humains, et qui sont agrégées par une méthoded'apprentissage de métrique. Dans le deuxième scénario, nous montrons nonseulement l'importance de la précision de la pose en 3D pour lareconnaissance d'actions, mais aussi que les deux tâches peuvent êtreefficacement effectuées par un seul réseau de neurones profond capabled'obtenir des résultats du niveau de l'état de l'art.De plus, nous démontrons que l'optimisation de bout en bout en utilisant lapose comme contrainte intermédiaire conduit à une précision plus élevée sur latâche de reconnaissance d'action que l'apprentissage séparé de ces tâches. Enfin, nous proposons une nouvellearchitecture adaptable pour l’estimation de la pose en 3D et la reconnaissancede l’actions simultanément et en temps réel. Cette architecture offre une gammede compromis performances vs vitesse avec une seule procédure d’entraînementmultitâche et multimodale
3D human action recognition is a challenging task due to the complexity ofhuman movements and to the variety on poses and actions performed by distinctsubjects. Recent technologies based on depth sensors can provide 3D humanskeletons with low computational cost, which is an useful information foraction recognition. However, such low cost sensors are restricted tocontrolled environment and frequently output noisy data. Meanwhile,convolutional neural networks (CNN) have shown significant improvements onboth action recognition and 3D human pose estimation from RGB images. Despitebeing closely related problems, the two tasks are frequently handled separatedin the literature. In this work, we analyze the problem of 3D human actionrecognition in two scenarios: first, we explore spatial and temporalfeatures from human skeletons, which are aggregated by a shallow metriclearning approach. In the second scenario, we not only show that precise 3Dposes are beneficial to action recognition, but also that both tasks can beefficiently performed by a single deep neural network and stillachieves state-of-the-art results. Additionally, wedemonstrate that optimization from end-to-end using poses as an intermediateconstraint leads to significant higher accuracy on the action task thanseparated learning. Finally, we propose a new scalable architecture forreal-time 3D pose estimation and action recognition simultaneously, whichoffers a range of performance vs speed trade-off with a single multimodal andmultitask training procedure
9

Sunde, Valfridsson Jonas. "Query By Example Keyword Spotting." Thesis, KTH, Skolan för elektroteknik och datavetenskap (EECS), 2021. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-299743.

Full text
APA, Harvard, Vancouver, ISO, and other styles
Abstract:
Voice user interfaces have been growing in popularity and with them an interest for open vocabulary keyword spotting. In this thesis we focus on one particular approach to open vocabulary keyword spotting, query by example keyword spotting. Three types of query by example keyword spotting approaches are described and evaluated: sequence distances, speech to phonemes and deep distance learning. Evaluation is done on a series of custom tasks designed to measure a variety of aspects. The Google Speech Commands benchmark is used for evaluation as well, this to make it more comparable to existing works. From the results, the deep distance learning approach seem most promising in most environments except when memory is very constrained; in which sequence distances might be considered. The speech to phonemes methods is lacking in the usability evaluation.
Röstgränssnitt har växt i populäritet och med dem ett intresse för öppenvokabulärnyckelordsigenkänning. I den här uppsatsen fokuserar vi på en specifik form av öppenvokabulärnyckelordsigenkänning, den s.k nyckelordsigenkänning- genom- exempel. Tre typer av nyckelordsigenkänning- genom- exempel metoder beskrivs och utvärderas: sekvensavstånd, tal till fonem samt djupavståndsinlärning. Utvärdering görs på konstruerade uppgifter designade att mäta en mängd olika aspekter hos metoderna. Google Speech Commands data används för utvärderingen också, detta för att göra det mer jämförbart mot existerade arbeten. Från resultaten framgår det att djupavståndsinlärning verkar mest lovande förutom i miljöer där resurser är väldigt begränsade; i dessa kan sekvensavstånd vara av intresse. Tal till fonem metoderna visar brister i användningsuvärderingen.
10

Swietojanski, Paweł. "Learning representations for speech recognition using artificial neural networks." Thesis, University of Edinburgh, 2016. http://hdl.handle.net/1842/22835.

Full text
APA, Harvard, Vancouver, ISO, and other styles
Abstract:
Learning representations is a central challenge in machine learning. For speech recognition, we are interested in learning robust representations that are stable across different acoustic environments, recording equipment and irrelevant inter– and intra– speaker variabilities. This thesis is concerned with representation learning for acoustic model adaptation to speakers and environments, construction of acoustic models in low-resource settings, and learning representations from multiple acoustic channels. The investigations are primarily focused on the hybrid approach to acoustic modelling based on hidden Markov models and artificial neural networks (ANN). The first contribution concerns acoustic model adaptation. This comprises two new adaptation transforms operating in ANN parameters space. Both operate at the level of activation functions and treat a trained ANN acoustic model as a canonical set of fixed-basis functions, from which one can later derive variants tailored to the specific distribution present in adaptation data. The first technique, termed Learning Hidden Unit Contributions (LHUC), depends on learning distribution-dependent linear combination coefficients for hidden units. This technique is then extended to altering groups of hidden units with parametric and differentiable pooling operators. We found the proposed adaptation techniques pose many desirable properties: they are relatively low-dimensional, do not overfit and can work in both a supervised and an unsupervised manner. For LHUC we also present extensions to speaker adaptive training and environment factorisation. On average, depending on the characteristics of the test set, 5-25% relative word error rate (WERR) reductions are obtained in an unsupervised two-pass adaptation setting. The second contribution concerns building acoustic models in low-resource data scenarios. In particular, we are concerned with insufficient amounts of transcribed acoustic material for estimating acoustic models in the target language – thus assuming resources like lexicons or texts to estimate language models are available. First we proposed an ANN with a structured output layer which models both context–dependent and context–independent speech units, with the context-independent predictions used at runtime to aid the prediction of context-dependent states. We also propose to perform multi-task adaptation with a structured output layer. We obtain consistent WERR reductions up to 6.4% in low-resource speaker-independent acoustic modelling. Adapting those models in a multi-task manner with LHUC decreases WERRs by an additional 13.6%, compared to 12.7% for non multi-task LHUC. We then demonstrate that one can build better acoustic models with unsupervised multi– and cross– lingual initialisation and find that pre-training is a largely language-independent. Up to 14.4% WERR reductions are observed, depending on the amount of the available transcribed acoustic data in the target language. The third contribution concerns building acoustic models from multi-channel acoustic data. For this purpose we investigate various ways of integrating and learning multi-channel representations. In particular, we investigate channel concatenation and the applicability of convolutional layers for this purpose. We propose a multi-channel convolutional layer with cross-channel pooling, which can be seen as a data-driven non-parametric auditory attention mechanism. We find that for unconstrained microphone arrays, our approach is able to match the performance of the comparable models trained on beamform-enhanced signals.
More sources

Books on the topic "Deep Distance Learning":

1

Terrell, Ian. Distant and deep: A report on the collaborative research and development of a distant and deep learning project. [London]: Middlesex University, School of Education, 1996.

Find full text
APA, Harvard, Vancouver, ISO, and other styles

Book chapters on the topic "Deep Distance Learning":

1

Agrebi, Maroi, Mondher Sendi, and Mourad Abed. "Deep Reinforcement Learning for Personalized Recommendation of Distance Learning." In Advances in Intelligent Systems and Computing, 597–606. Cham: Springer International Publishing, 2019. http://dx.doi.org/10.1007/978-3-030-16184-2_57.

Full text
APA, Harvard, Vancouver, ISO, and other styles
2

Dinakaran, Ranjith K., Philip Easom, Ahmed Bouridane, Li Zhang, Richard Jiang, Fozia Mehboob, and Abdul Rauf. "Deep Learning Based Pedestrian Detection at Distance in Smart Cities." In Advances in Intelligent Systems and Computing, 588–93. Cham: Springer International Publishing, 2019. http://dx.doi.org/10.1007/978-3-030-29513-4_43.

Full text
APA, Harvard, Vancouver, ISO, and other styles
3

Li, Huiyu, Xiabi Liu, Said Boumaraf, Xiaopeng Gong, Donghai Liao, and Xiaohong Ma. "Deep Distance Map Regression Network with Shape-Aware Loss for Imbalanced Medical Image Segmentation." In Machine Learning in Medical Imaging, 231–40. Cham: Springer International Publishing, 2020. http://dx.doi.org/10.1007/978-3-030-59861-7_24.

Full text
APA, Harvard, Vancouver, ISO, and other styles
4

Ngo, Tuan Anh, and Gustavo Carneiro. "Fully Automated Segmentation Using Distance Regularised Level Set and Deep-Structured Learning and Inference." In Deep Learning and Convolutional Neural Networks for Medical Image Computing, 197–224. Cham: Springer International Publishing, 2017. http://dx.doi.org/10.1007/978-3-319-42999-1_12.

Full text
APA, Harvard, Vancouver, ISO, and other styles
5

Lamash, Yechiel, Sila Kurugol, and Simon K. Warfield. "Semi-automated Extraction of Crohns Disease MR Imaging Markers Using a 3D Residual CNN with Distance Prior." In Deep Learning in Medical Image Analysis and Multimodal Learning for Clinical Decision Support, 218–26. Cham: Springer International Publishing, 2018. http://dx.doi.org/10.1007/978-3-030-00889-5_25.

Full text
APA, Harvard, Vancouver, ISO, and other styles
6

Hou, Jie, Tianqi Wu, Zhiye Guo, Farhan Quadir, and Jianlin Cheng. "The MULTICOM Protein Structure Prediction Server Empowered by Deep Learning and Contact Distance Prediction." In Methods in Molecular Biology, 13–26. New York, NY: Springer US, 2020. http://dx.doi.org/10.1007/978-1-0716-0708-4_2.

Full text
APA, Harvard, Vancouver, ISO, and other styles
7

Chopard, Daphné, and Irena Spasić. "A Deep Learning Approach to Self-expansion of Abbreviations Based on Morphology and Context Distance." In Statistical Language and Speech Processing, 71–82. Cham: Springer International Publishing, 2019. http://dx.doi.org/10.1007/978-3-030-31372-2_6.

Full text
APA, Harvard, Vancouver, ISO, and other styles
8

Vinoth, N., A. Ganesh Ram, M. Vijayakarthick, and S. Meyyappan. "Automatic Mask Detection and Social Distance Alerting Based on a Deep-Learning Computer Vision Algorithm." In Computational Modelling and Imaging for SARS-CoV-2 and COVID-19, 73–93. Boca Raton: CRC Press, 2021. http://dx.doi.org/10.1201/9781003142584-5-5.

Full text
APA, Harvard, Vancouver, ISO, and other styles
9

Liu, Zhuangzhuang, Mingming Ren, Zhiheng Niu, Gang Wang, and Xiaoguang Liu. "DeepED: A Deep Learning Framework for Estimating Evolutionary Distances." In Artificial Neural Networks and Machine Learning – ICANN 2020, 325–36. Cham: Springer International Publishing, 2020. http://dx.doi.org/10.1007/978-3-030-61609-0_26.

Full text
APA, Harvard, Vancouver, ISO, and other styles
10

Asami, Yasushi. "Introduction: City Planning and New Technology." In New Frontiers in Regional Science: Asian Perspectives, 261–65. Singapore: Springer Singapore, 2021. http://dx.doi.org/10.1007/978-981-15-8848-8_17.

Full text
APA, Harvard, Vancouver, ISO, and other styles
Abstract:
AbstractIn Part III, titled “City Planning and New Technology,” we discuss two topics, namely, compact cities and real estate technology in Japan.Promotion of compact cities is regarded as a high priority issue in urban policies in the era of population decrease. The Act on Special Measures concerning Urban Reconstruction in 2014 was revised to institutionalize the framework for the Location Normalization Plan, a plan for local governments to build compact cities to manage population decline and aging urban infrastructure while placing less burden on environment. Three chapters are devoted to issues related to this movement. In Chap.10.1007/978-981-15-8848-8_18, Ishikawa (2020) discusses how urban functions can be guided by residents’ perspectives. To build a compact city, various day-to-day services must be placed proximal to residential areas; however, some services must be placed at a certain distance from residences because of land use restrictions. Therefore, we must determine the uses allowed in residential areas. In Chap.10.1007/978-981-15-8848-8_19, Morimoto (2020) discusses the history of major contributions made by the development of transportation facilities to urban spread, the important role of traffic facilities to guide land use toward desirable purposes, and impact of self-driving vehicles on land use. In Chap.10.1007/978-981-15-8848-8_20, Ogushi (2020) explains how the Location Normalization Plan in Niigata City was formed in detail.Real estate technology refers to real estate business-related services that use new technology. Several new services based on new technology have been introduced in the field of real estate in Japan. Three chapters are devoted to issues related to real estate technology. In Chap.10.1007/978-981-15-8848-8_21, Narimoto (2020) explains the outline of real estate technology services in Japan and identifies legal problems associated with handling of information. In Chap.10.1007/978-981-15-8848-8_22, Nishio and Ito (2020) report on creating a sky view factor calculating system that uses Google Street View. Sky view factor is a term that refers to a configuration factor for the amount of sky in a hypothetical hemisphere. In Chap.10.1007/978-981-15-8848-8_23, Kiyota (2020) explains the transition of neural network research and characteristics of deep learning and introduces a system that detects category inconsistencies in real estate property photographs submitted by real estate companies by using deep learning and a system that detects indexes associated with ease of living based on property photographs.

Conference papers on the topic "Deep Distance Learning":

1

Rizi, Fatemeh Salehi, Joerg Schloetterer, and Michael Granitzer. "Shortest Path Distance Approximation Using Deep Learning Techniques." In 2018 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining (ASONAM). IEEE, 2018. http://dx.doi.org/10.1109/asonam.2018.8508763.

Full text
APA, Harvard, Vancouver, ISO, and other styles
2

Gundogdu, Erhan, Berkan Solmaz, Aykut Koc, Veysel Yucesoy, and A. Aydin Alatan. "Deep distance metric learning for maritime vessel identification." In 2017 25th Signal Processing and Communications Applications Conference (SIU). IEEE, 2017. http://dx.doi.org/10.1109/siu.2017.7960170.

Full text
APA, Harvard, Vancouver, ISO, and other styles
3

Akhloufi, Moulay A., and Axel-Christian Guei. "Deep learning for face recognition at a distance." In Disruptive Technologies in Information Sciences, edited by Misty Blowers, Russell D. Hall, and Venkateswara R. Dasari. SPIE, 2018. http://dx.doi.org/10.1117/12.2304896.

Full text
APA, Harvard, Vancouver, ISO, and other styles
4

Sandoval-Bravo, Luis Alberto, Volodymyr I. Ponomaryov, Rogelio Reyes-Reyes, and Clara Cruz-Ramos. "Coverless image steganography framework using distance local binary pattern and convolutional neural network." In Real-Time Image Processing and Deep Learning 2020, edited by Nasser Kehtarnavaz and Matthias F. Carlsohn. SPIE, 2020. http://dx.doi.org/10.1117/12.2556310.

Full text
APA, Harvard, Vancouver, ISO, and other styles
5

Mahalunkar, Abhijit, and John Kelleher. "Multi-Element Long Distance Dependencies: Using SPk Languages to Explore the Characteristics of Long-Distance Dependencies." In Proceedings of the Workshop on Deep Learning and Formal Languages: Building Bridges. Stroudsburg, PA, USA: Association for Computational Linguistics, 2019. http://dx.doi.org/10.18653/v1/w19-3904.

Full text
APA, Harvard, Vancouver, ISO, and other styles
6

Sun, Wenjie, Zheng Shan, Fudong Liu, Meng Qiao, Hairen Gui, and Xingwei Li. "Similarity Measure for Binary Function Based on Graph Mover’s Distance." In 2020 International Conference on Computer Vision, Image and Deep Learning (CVIDL). IEEE, 2020. http://dx.doi.org/10.1109/cvidl51233.2020.00-90.

Full text
APA, Harvard, Vancouver, ISO, and other styles
7

Shen, Xiaobo, Weiwei Liu, Yong Luo, Yew-Soon Ong, and Ivor W. Tsang. "Deep Discrete Prototype Multilabel Learning." In Twenty-Seventh International Joint Conference on Artificial Intelligence {IJCAI-18}. California: International Joint Conferences on Artificial Intelligence Organization, 2018. http://dx.doi.org/10.24963/ijcai.2018/371.

Full text
APA, Harvard, Vancouver, ISO, and other styles
Abstract:
kNN embedding methods, such as the state-of-the-art LM-kNN, have shown impressive results in multi-label learning. Unfortunately, these approaches suffer expensive computation and memory costs in large-scale settings. To fill this gap, this paper proposes a novel deep prototype compression, i.e., DBPC for fast multi-label prediction. DBPC compresses the database into a small set of short discrete prototypes, and uses the prototypes for prediction. The benefit of DBPC comes from two aspects: 1) The number of distance comparisons are reduced in the prototype; 2) The distance computation cost is significantly decreased in the reduced space. We propose to jointly learn the deep latent subspace and discrete prototypes within one framework. The encoding and decoding neural networks are employed to make deep discrete prototypes well represent the instances and labels. Extensive experiments on several large-scale datasets demonstrate that DBPC achieves several orders of magnitude lower storage and prediction complexity than state-of-the-art multi-label methods, while achieving competitive accuracy.
8

Zhen Zuo and Gang Wang. "Recognizing trees at a distance with discriminative deep feature learning." In 2013 9th International Conference on Information, Communications & Signal Processing (ICICS). IEEE, 2013. http://dx.doi.org/10.1109/icics.2013.6782881.

Full text
APA, Harvard, Vancouver, ISO, and other styles
9

Liu, Hongye, Yonghong Tian, Yaowei Wang, Lu Pang, and Tiejun Huang. "Deep Relative Distance Learning: Tell the Difference between Similar Vehicles." In 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). IEEE, 2016. http://dx.doi.org/10.1109/cvpr.2016.238.

Full text
APA, Harvard, Vancouver, ISO, and other styles
10

Couturier, Raphael, Michel Salomon, Elie Abou Zeid, and Chady Abou Jaoude. "Using Deep Learning for Object Distance Prediction in Digital Holography." In 2021 International Conference on Computer, Control and Robotics (ICCCR). IEEE, 2021. http://dx.doi.org/10.1109/icccr49711.2021.9349275.

Full text
APA, Harvard, Vancouver, ISO, and other styles

To the bibliography