Improved Classification Based on Deep Belief Networks

For better classification generative models are used to initialize the model and model features before training a classifier. Typically it is needed to solve separate unsupervised and supervised learning problems. Generative restricted Boltzmann machines and deep belief networks are widely used for unsupervised learning. We developed several supervised models based on DBN in order to improve this two-phase strategy. Modifying the loss function to account for expectation with respect to the underlying generative model, introducing weight bounds, and multi-level programming are applied in model development. The proposed models capture both unsupervised and supervised objectives effectively. The computational study verifies that our models perform better than the two-phase training approach.

[1]  Rong Huang,et al.  Web spam classification method based on deep belief networks , 2018, Expert Syst. Appl..

[2]  Heba F. Eid,et al.  Hybrid Intelligent Intrusion Detection Scheme , 2011 .

[3]  Thomas Hofmann,et al.  Greedy Layer-Wise Training of Deep Networks , 2007 .

[4]  Ryan P. Adams,et al.  Training Restricted Boltzmann Machines on Word Observations , 2012, ICML.

[5]  Jens Myrup Pedersen,et al.  Advances in intelligent and soft computing , 2011 .

[6]  Nitish V. Thakor IEEE Transactions on Neural Systems and Rehabilitation Engineering: Editorial , 2006 .

[7]  Mohammad Norouzi,et al.  Stacks of convolutional Restricted Boltzmann Machines for shift-invariant feature learning , 2009, CVPR.

[8]  Peter V. Gehler,et al.  The rate adapting poisson model for information retrieval and object recognition , 2006, ICML.

[9]  M. V. Rossum,et al.  In Neural Computation , 2022 .

[10]  Christopher Joseph Pal,et al.  Multi-Conditional Learning: Generative/Discriminative Training for Clustering and Classification , 2006, AAAI.

[11]  Geoffrey E. Hinton Training Products of Experts by Minimizing Contrastive Divergence , 2002, Neural Computation.

[12]  Yoshua Bengio,et al.  Classification using discriminative restricted Boltzmann machines , 2008, ICML '08.

[13]  Michael I. Jordan,et al.  Advances in Neural Information Processing Systems 30 , 1995 .

[14]  Kenji Doya,et al.  Expected energy-based restricted Boltzmann machine for classification , 2015, Neural Networks.

[15]  A. Sayed,et al.  Foundations and Trends ® in Machine Learning > Vol 7 > Issue 4-5 Ordering Info About Us Alerts Contact Help Log in Adaptation , Learning , and Optimization over Networks , 2011 .

[16]  Geoffrey E. Hinton,et al.  Application of Deep Belief Networks for Natural Language Understanding , 2014, IEEE/ACM Transactions on Audio, Speech, and Language Processing.

[17]  Razvan Pascanu,et al.  Learning Algorithms for the Classification Restricted Boltzmann Machine , 2012, J. Mach. Learn. Res..

[18]  Rong Yan,et al.  Mining Associated Text and Images with Dual-Wing Harmoniums , 2005, UAI.

[19]  Yee Whye Teh,et al.  A Fast Learning Algorithm for Deep Belief Nets , 2006, Neural Computation.

[20]  Na Lu,et al.  A Deep Learning Scheme for Motor Imagery Classification based on Restricted Boltzmann Machines , 2017, IEEE Transactions on Neural Systems and Rehabilitation Engineering.

[21]  Tobias Scheffer,et al.  International Conference on Machine Learning (ICML-99) , 1999, Künstliche Intell..

[22]  Yoshua. Bengio,et al.  Learning Deep Architectures for AI , 2007, Found. Trends Mach. Learn..

[23]  Geoffrey E. Hinton,et al.  Generative versus discriminative training of RBMs for classification of fMRI images , 2008, NIPS.

[24]  Geoffrey E. Hinton,et al.  Reducing the Dimensionality of Data with Neural Networks , 2006, Science.

[25]  Li Li,et al.  Classification of Cytochrome P450 1A2 Inhibitors and Noninhibitors Based on Deep Belief Network , 2017, Int. J. Comput. Intell. Appl..

[26]  Christian Igel,et al.  An Introduction to Restricted Boltzmann Machines , 2012, CIARP.

[27]  Diego Klabjan,et al.  Regularization for Unsupervised Deep Neural Nets , 2016, AAAI.

[28]  Kyunghyun Cho,et al.  Improved Learning Algorithms for Restricted Boltzmann Machines , 2011 .