Results 111 to 120 of about 22,598 (163)

Normal sparse Deep Belief Network

2015 International Joint Conference on Neural Networks (IJCNN), 2015
Nowadays this is very popular to use deep architectures in machine learning. Deep Belief Networks (DBNs) have deep architectures to create a powerful generative model using training data. Deep Belief Networks can be used in classification and feature learning.
Mohammad Ali Keyvanrad, Mohammad Mehdi Homayounpour   +1 more
openaire   +1 more source

An ontology-based deep belief network model

Computing, 2021
The end-to-end model has a wide range of applications in the fields of image recognition, natural language processing and speech recognition. The main benefit of this model is that the structure is a black box, and industrial users need only amend the inputs and outputs to obtain better performance for various applications.
Xiulei Liu, Ruoyu Chen 0002, Qiang Tong 0001, Zhihui Qin, Qinfu Shi, Li Duan   +5 more
openaire   +1 more source

Deep belief networks with self-adaptive sparsity

Applied Intelligence, 2021
To have the sparsity of deep neural networks is crucial, which can improve the learning ability of them, especially for application to high-dimensional data with small sample size. Commonly used regularization terms for keeping the sparsity of deep neural networks are based on L1-norm or L2-norm; however, they are not the most reasonable substitutes of
Chen Qiao, Lan Yang 0010, Yan Shi, Hanfeng Fang, Yanmei Kang   +4 more
openaire   +1 more source

Deep Belief Networks Oriented Clustering

2015 10th International Conference on Intelligent Systems and Knowledge Engineering (ISKE), 2015
Deep learning has been popular for a few years, and it shows great capability on unsupervised leaning of representation. Deep belief network consists of multi layers of restricted Boltzmann machine(RBM) and a deep auto-encoder, which uses a stack architecture learning feature layer by layer.
Qi Yang, Hongjun Wang 0002, Tianrui Li 0001, Yan Yang 0001   +3 more
openaire   +1 more source

Deep Belief Networks and deep learning

Proceedings of 2015 International Conference on Intelligent Computing and Internet of Things, 2015
Deep Belief Network is an algorithm among deep learning. It is an effective method of solving the problems from neural network with deep layers, such as low velocity and the overfitting phenomenon in learning. In this paper, we will introduce how to process a Deep Belief Network by using Restricted Boltzmann Machines.
null Yuming Hua, null Junhai Guo, null Hua Zhao   +2 more
openaire   +1 more source

Deep Belief Networks Are Compact Universal Approximators

Neural Computation, 2010
Deep belief networks (DBN) are generative models with many layers of hidden causal variables, recently introduced by Hinton, Osindero, and Teh ( 2006 ), along with a greedy layer-wise unsupervised learning algorithm. Building on Le Roux and Bengio ( 2008 ) and Sutskever and Hinton ( 2008 ), we show that deep but narrow generative networks do not ...
Nicolas Le Roux, Yoshua Bengio
openaire   +1 more source

Chart classification by combining deep convolutional networks and deep belief networks

2015 13th International Conference on Document Analysis and Recognition (ICDAR), 2015
Chart classification is the foundation of chart analysis and document understanding. In this paper, we propose a novel framework to classify charts by combining convolutional networks and deep belief networks. In the framework, we firstly extract deep hidden features of charts, which are taken from the fully-connected layer of deep convolutional ...
Xiao Liu 0012, Binbin Tang, Zhenyang Wang, Xianghua Xu, Shiliang Pu, Dapeng Tao, Mingli Song   +6 more
openaire   +1 more source

Deep Belief Networks for Financial Prediction

2011
Financial business prediction has lately raised a great interest due to the recent world crisis events. In spite of the many advanced shallow computational methods that have extensively been proposed, most algorithms have not yet attained a desirable level of applicability.
Bernardete Ribeiro, Noel Lopes
openaire   +1 more source

Spiking Convolutional Deep Belief Networks

2017
Understanding visual input as perceived by humans is a challenging task for machines. Today, most successful methods work by learning features from static images. Based on classical artificial neural networks, those methods are not adapted to process event streams as provided by the Dynamic Vision Sensor (DVS).
Jacques Kaiser, David Zimmerer, Juan Camilo Vasquez Tieck, Stefan Ulbrich, Arne Roennau, Rüdiger Dillmann   +5 more
openaire   +1 more source

Acoustic Modeling Using Deep Belief Networks

IEEE Transactions on Audio, Speech, and Language Processing, 2012
Gaussian mixture models are currently the dominant technique for modeling the emission distribution of hidden Markov models for speech recognition. We show that better phone recognition on the TIMIT dataset can be achieved by replacing Gaussian mixture models by deep neural networks that contain many layers of features and a very large number of ...
Abdel-rahman Mohamed, George E. Dahl, Geoffrey E. Hinton   +2 more
openaire   +1 more source