Filters








2,702 Hits in 5.5 sec

Sparse Boltzmann Machines with Structure Learning as Applied to Text Analysis [article]

Zhourong Chen, Nevin L. Zhang, Dit-Yan Yeung, Peixian Chen
2018 arXiv   pre-print
We present a method for learning what we call Sparse Boltzmann Machines, where each hidden unit is connected to a subset of the visible units instead of all of them.  ...  We are interested in exploring the possibility and benefits of structure learning for deep models. As the first step, this paper investigates the matter for Restricted Boltzmann Machines (RBMs).  ...  The target domain is unsupervised text analysis. We present an algorithm for learning what we call Sparse Boltzmann Machines.  ... 
arXiv:1609.05294v3 fatcat:m6pwzujikjdfvi7zuuhwbisi2a

Sparse Boltzmann Machines with Structure Learning as Applied to Text Analysis

Zhourong Chen, Nevin Zhang, Dit-Yan Yeung, Peixian Chen
2017 PROCEEDINGS OF THE THIRTIETH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE AND THE TWENTY-EIGHTH INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE  
We present a method for learning what we call Sparse Boltzmann Machines, where each hidden unit is connected to a subset of the visible units instead of all of them.  ...  We are interested in exploring the possibility and benefits of structure learning for deep models. As the first step, this paper investigates the matter for Restricted Boltzmann Machines (RBMs).  ...  The target domain is unsupervised text analysis. We present an algorithm for learning what we call Sparse Boltzmann Machines (SBMs).  ... 
doi:10.1609/aaai.v31i1.10773 fatcat:bdjyu52335erpo4rbzsqjf5hum

Applying deep learning on electronic health records in Swedish to predict healthcare-associated infections

Olof Jacobson, Hercules Dalianis
2016 Proceedings of the 15th Workshop on Biomedical Natural Language Processing  
Using natural language processing and machine learning applied on electronic patient records is one approach that has been shown to work.  ...  Specifically we implemented a network of stacked sparse auto encoders and a network of stacked restricted Boltzmann machines.  ...  We would also like to thank Claudia Ehrentraut and Hideyuki Tanushi for their ground breaking work to construct the Stockholm EPR Detect-HAI Corpus.  ... 
doi:10.18653/v1/w16-2926 dblp:conf/bionlp/JacobsonD16 fatcat:ovlrsrnwjvaafdeqvek3ahbbiy

Text feature extraction based on deep learning: a review

Hong Liang, Xiao Sun, Yunlei Sun, Yuan Gao
2017 EURASIP Journal on Wireless Communications and Networking  
As a new feature extraction method, deep learning has made achievements in text mining.  ...  To hand-design, an effective feature is a lengthy process, but aiming at new applications, deep learning enables to acquire new effective feature representation from training data.  ...  Publisher's Note Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.  ... 
doi:10.1186/s13638-017-0993-1 pmid:29263717 pmcid:PMC5732309 fatcat:bqyk3wddqbebdfeki72myn5p2y

Survey on Neural Network Architectures with Deep Learning

Smys S., Joy Iong Zong Chen, Subarna Shakya
2020 Journal of Soft Computing Paradigm  
In particular deep learning is one of the cost efficient, effective supervised learning model, which can be applied to various complicated issues.  ...  In the present research era, machine learning is an important and unavoidable zone where it provides better solutions to various domains.  ...  This learning algorithms helps to determine the model structure with minimum learning parameters compared to other architecture models.  ... 
doi:10.36548/jscp.2020.3.007 fatcat:saxneqmonvdy7iv6qzkpkoii3y

Sparse generative modeling via parameter-reduction of Boltzmann machines: application to protein-sequence families [article]

Pierre Barrat-Charlaix, Anna Paola Muntoni, Kai Shimagaki, Martin Weigt, Francesco Zamponi
2021 arXiv   pre-print
Boltzmann machines (BM) are widely used as generative models.  ...  This choice, typical of what is known as Direct Coupling Analysis, has been successful for predicting residue contacts in the three-dimensional structure, mutational effects, and in generating new functional  ...  ACKNOWLEDGMENTS We would like to thank Matteo Bisardi, Simona Cocco, Yaakov Kleeorin, Rémi Monasson, Rama Ranghanatan, Olivier Rivoire and Jeanne Trinquier for discussions related to this work.  ... 
arXiv:2011.11259v3 fatcat:ql7mxpeo2fbgda3dhfrgt3sxey

Novel Methods Based on Deep Learning Applied to Condition Monitoring in Smart Manufacturing Processes [chapter]

Francisco Arellano Espitia, Lucia Ruiz Soto
2020 New Trends in the Use of Artificial Intelligence for the Industry 4.0  
In recent years, various deep learning techniques have been applied successfully in different areas of research, such as image recognition, robotics, and the detection of abnormalities in clinical studies  ...  With the current demand of the industry and the increasing complexity of the systems, it is vital to incorporate CBM methodologies that are capable of facing the variability and complexity of manufacturing  ...  An example of application of schemes based on deep learning applied to industrial machines is presented in [12] ; in this study, they implemented a structure of deep learning known as a stacked denoising  ... 
doi:10.5772/intechopen.89570 fatcat:n7f3yfs43fgz3pfmeuyxxalkkq

Towards Sparsity and Selectivity: Bayesian Learning of Restricted Boltzmann Machine for Early Visual Features [chapter]

Hanchen Xiong, Sandor Szedmak, Antonio Rodríguez-Sánchez, Justus Piater
2014 Lecture Notes in Computer Science  
This paper exploits how Bayesian learning of restricted Boltzmann machine (RBM) can discover more biologically-resembled early visual features.  ...  According to our empirical results, the visual features learned from the proposed Bayesian framework yield better discriminative and generalization capability than the ones learned with maximum likelihood  ...  Restricted Boltzmann Machine The restricted Boltzmann machine (RBM) is a two-layer, bipartite neural network, it is a "restricted version" of the Boltzmann machine with only interconnections between hidden  ... 
doi:10.1007/978-3-319-11179-7_53 fatcat:z4r7nuy7zvcuvgrsbdqflwfi3u

Simulating disordered quantum systems via dense and sparse restricted Boltzmann machines [article]

S. Pilati, P. Pieri
2020 arXiv   pre-print
In recent years, generative artificial neural networks based on restricted Boltzmann machines (RBMs) have been successfully employed as accurate and flexible variational wave functions for clean quantum  ...  We assess the performance of sparse RBMs as a function of the range of the allowed connections, and compare it with the one of dense RBMs.  ...  P. acknowledge financial support from the FAR2018 project titled "Supervised machine learning for quantum matter and computational docking" of the University of Camerino and from the Italian MIUR under  ... 
arXiv:2003.09765v1 fatcat:zl3v3gowivgpvipy4nspt4cziq

Boltzmann Machines and Denoising Autoencoders for Image Denoising [article]

Kyunghyun Cho
2013 arXiv   pre-print
In this paper, we propose that another popular family of models in the field of deep learning, called Boltzmann machines, can perform image denoising as well as, or in certain cases of high level of noise  ...  We empirically evaluate the two models on three different sets of images with different types and levels of noise. Throughout the experiments we also examine the effect of the depth of the models.  ...  Subsequently, a shrinkage nonlinear function is applied to the estimated sparse code elements to suppress those elements with small absolute magnitude.  ... 
arXiv:1301.3468v6 fatcat:ubupuw5xpvdtlhfj546bhlwsta

MULTI-MODAL RETRIEVAL IN NEWS FEED APP USING GCDL TECHNIQUE

2017 International Journal of Recent Trends in Engineering and Research  
Existing methods proposed to use Canonical Correlation Analysis (CCA), manifolds learning, dual-wing harmoniums, deep autoencoder, and deep Boltzmann machine to approach the task.  ...  Since each modality having different representation methods and correlational structures, a variety of methods studied the problem from the aspect of learning correlations between different modalities.  ...  Latent semantic sparse hashing proposed the use of Matrix Factorization to represent text and sparse coding to capture the salient structures of images.  ... 
doi:10.23883/ijrter.2017.3365.aeikk fatcat:6dmfmfsmtbaejale6t63ts7may

Resolution and Relevance Trade-offs in Deep Learning [article]

Juyong Song, Matteo Marsili, Junghyo Jo
2018 arXiv   pre-print
Deep learning has been successfully applied to various tasks, but its underlying mechanism remains unclear.  ...  Representations with minimal noise, at a given level of similarity (resolution), are those that maximise the relevance.  ...  For a restricted Boltzmann machine (RBM) with 50 hidden nodes, we considered the sparseness of the network in terms of connectivities and activities.  ... 
arXiv:1710.11324v2 fatcat:womweyeaifffldbx6xxehws6da

Design of Human Resource Management System Based on Deep Learning

Jinlong Li, Zhe Zhou, Zhao Kaifa
2022 Computational Intelligence and Neuroscience  
However, there are few related works in the field of deep learning applied to human resource management system at present.  ...  Therefore, this paper studies and improves the recommendation algorithm based on deep learning and applies it to the field of human resources recommendation.  ...  A restricted Boltzmann machine (RBM) is a structural model with a full connection between layers and no connection within layers. Its structure is shown in Figure 2 .  ... 
doi:10.1155/2022/9122881 pmid:35909850 pmcid:PMC9329010 fatcat:7n2baj7xp5dwbbztyqwph6jsde

Simulating disordered quantum Ising chains via dense and sparse restricted Boltzmann machines

S. Pilati, P. Pieri
2020 Physical review. E  
In recent years, generative artificial neural networks based on restricted Boltzmann machines (RBMs) have been successfully employed as accurate and flexible variational wave functions for clean quantum  ...  We assess the performance of sparse RBMs as a function of the range of the allowed connections, and we compare it with that of dense RBMs.  ...  We have found that restricted Boltzmann machines with a local sparse connectivity reach higher accuracy, when trained via unsupervised learning, compared to the standard dense RBMs with all-to-all interlayer  ... 
doi:10.1103/physreve.101.063308 pmid:32688495 fatcat:fggqgbtkazfcpdotys6pxat6xm

Learning Parts-based Representations with Nonnegative Restricted Boltzmann Machine

Tu Dinh Nguyen, Truyen Tran, Dinh Q. Phung, Svetha Venkatesh
2013 Asian Conference on Machine Learning  
Of current representation learning schemes, restricted Boltzmann machines (RBMs) have proved to be highly effective in unsupervised settings.  ...  The success of any machine learning system depends critically on effective representations of data.  ...  For the semantic analysis of text, our proposed model is able to discover plausible thematic features.  ... 
dblp:conf/acml/NguyenTPV13 fatcat:h3jo7zyukrbedf2wxjrl6sj7ba
« Previous Showing results 1 — 15 out of 2,702 results