Results 121 to 130 of about 22,598 (163)
Some of the next articles are maybe not open access.
Face recognition with improved deep belief networks
2017 13th International Conference on Natural Computation, Fuzzy Systems and Knowledge Discovery (ICNC-FSKD), 2017Deep learning techniques have become the state-of-the-art approach for classification in artificial intelligence, and applied in many widespread subjects. Deep Belief Networks (DBNs) are one of the most successful models. DBNs consist of many layers of hidden factors along with a greedy layer-wise unsupervised learning algorithm.
Rong Fan, Wenxin Hu
openaire +1 more source
A study of transformation-invariances of deep belief networks
The 2013 International Joint Conference on Neural Networks (IJCNN), 2013In order to learn transformation-invariant features, several effective deep architectures like hierarchical feature learning and variant Deep Belief Networks (DBN) have been proposed. Considering the complexity of those variants, people are interested in whether DBN itself has transformation-invariances.
Zheng Shou, Yuhao Zhang, Hengjin Cai
openaire +1 more source
Audio steganalysis using deep belief networks
International Journal of Speech Technology, 2016This paper presents a new steganalysis method that uses a deep belief network (DBN) as a classifier for audio files. It has been tested on three steganographic techniques: StegHide, Hide4PGP and FreqSteg. The results were compared to two other existing robust steganalysis methods based on support vector machines (SVMs) and Gaussian mixture models (GMMs)
Catherine Paulin +2 more
openaire +1 more source
Pseudo Boosted Deep Belief Network
2016A computationally efficient method to improve classification performance of a Deep Belief Network (DBN) is introduced. In the Pseudo Boost Deep Belief Network (PB-DBN), top layers are boosted while lower layers of the base classifiers share weights for feature extraction.
Tiehang Duan, Sargur N. Srihari
openaire +1 more source
Deep belief networks for predicting corporate defaults
2015 24th Wireless and Optical Communication Conference (WOCC), 2015This paper provides a new perspective on the default prediction problem using deep learning algorithms. Via the advantages of deep learning, the representable factors of input data will no longer need to be explicitly extracted, but can be implicitly learned by the deep learning algorithms.
Shu-Hao Yeh +2 more
openaire +1 more source
An Improved Deep Belief Network Prediction Method
2018 IEEE/ACIS 17th International Conference on Computer and Information Science (ICIS), 2018Deep belief network applying unsupervised methods of greedy layer training, from the training set automatic feature extraction value, will cause the error by layer transfer, thus affecting the accuracy of the model prediction, in order to solve this problem, proposed using conjugate gradient algorithm in gradient descent can accelerate the convergence ...
Yanchao Sun +3 more
openaire +1 more source
2015
This chapter covers successful applications in deep learning with remarkable capability to generate sophisticated and invariant features from raw input signal data. New insights of the visual cortex and studies in the relations between the connectivity found in the brain and mechanisms for mind inference have enlightened the development of deep neural ...
Noel Lopes, Bernardete Ribeiro
openaire +1 more source
This chapter covers successful applications in deep learning with remarkable capability to generate sophisticated and invariant features from raw input signal data. New insights of the visual cortex and studies in the relations between the connectivity found in the brain and mechanisms for mind inference have enlightened the development of deep neural ...
Noel Lopes, Bernardete Ribeiro
openaire +1 more source
Object Recognition Base on Deep Belief Network
2015 10th International Conference on Intelligent Systems and Knowledge Engineering (ISKE), 2015Event ontology is a general knowledge base constructed by event as the basic knowledge unit for computer communication. Event contains six elements which are action, object, time, environment, assertion and language performance. In this paper, we mainly discuss object elements recognition.
Yajun Zhang +3 more
openaire +1 more source
Optimized deep belief networks on CUDA GPUs
2015 International Joint Conference on Neural Networks (IJCNN), 2015A deep belief network (DBN) is an important branch of deep learning models and has been successfully applied in many machine learning and pattern recognition fields such as computer vision and speech recognition. However, the training of billions of parameters in DBN is computationally challenging for modern central processing units (CPUs).
Teng Li 0010 +4 more
openaire +1 more source
Classification of Electrocardiogram Signals with Deep Belief Networks
2014 IEEE 17th International Conference on Computational Science and Engineering, 2014This paper introduces an electrocardiogram beat classification method based on deep belief networks. This method includes two parts: feature extraction and classification. In the feature extraction part, features are extracted from the original electrocardiogram signal: including features extracted by deep belief networks and timing interval features ...
Huanhuan Meng, Yue Zhang
openaire +1 more source