Guided Layer-wise Learning for Deep Models using Side Information

Training of deep models for classification tasks is hindered by local minima problems and vanishing gradients, while unsupervised layer-wise pretraining does not exploit information from class labels. Here, we propose a new regularization technique, called diversifying regularization (DR), which applies a penalty on hidden units at any layer if they obtain similar features for different types of data. For generative models, DR is defined as divergence over the variational posteriori distributions and included in the maximum likelihood estimation as a prior. Thus, DR includes class label information for greedy pretraining of deep belief networks which result in a better weight initialization for fine-tuning methods. On the other hand, for discriminative training of deep neural networks, DR is defined as a distance over the features and included in the learning objective. With our experimental tests, we show that DR can help the backpropagation to cope with vanishing gradient problems and to provide faster convergence and smaller generalization errors.

[1]  Pascal Vincent,et al.  The Difficulty of Training Deep Architectures and the Effect of Unsupervised Pre-Training , 2009, AISTATS.

[2]  Yoshua Bengio,et al.  Exploring Strategies for Training Deep Neural Networks , 2009, J. Mach. Learn. Res..

[3]  Oliver Brock,et al.  Contextual Learning , 2015, ArXiv.

[4]  Alan L. Yuille,et al.  The Convergence of Contrastive Divergences , 2004, NIPS.

[5]  Hugo Larochelle,et al.  Efficient Learning of Deep Boltzmann Machines , 2010, AISTATS.

[6]  Yoshua Bengio,et al.  Greedy Layer-Wise Training of Deep Networks , 2006, NIPS.

[7]  Haizhou Li,et al.  An SVM Kernel With GMM-Supervector Based on the Bhattacharyya Distance for Speaker Recognition , 2009, IEEE Signal Processing Letters.

[8]  Nando de Freitas,et al.  An Introduction to MCMC for Machine Learning , 2004, Machine Learning.

[9]  Geoffrey E. Hinton,et al.  Deep Boltzmann Machines , 2009, AISTATS.

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

[11]  Kurt Hornik,et al.  Approximation capabilities of multilayer feedforward networks , 1991, Neural Networks.

[12]  Carl Doersch,et al.  Tutorial on Variational Autoencoders , 2016, ArXiv.

[13]  Tijmen Tieleman,et al.  Training restricted Boltzmann machines using approximations to the likelihood gradient , 2008, ICML '08.

[14]  Michael I. Jordan,et al.  An Introduction to Variational Methods for Graphical Models , 1999, Machine Learning.

[15]  Geoffrey E. Hinton,et al.  Deep, Narrow Sigmoid Belief Networks Are Universal Approximators , 2008, Neural Computation.

[16]  Yoshua Bengio,et al.  Gradient-based learning applied to document recognition , 1998, Proc. IEEE.

[17]  D. Hubel,et al.  Receptive fields, binocular interaction and functional architecture in the cat's visual cortex , 1962, The Journal of physiology.

[18]  Radford M. Neal Connectionist Learning of Belief Networks , 1992, Artif. Intell..

[19]  Chulhee Lee,et al.  Feature extraction based on the Bhattacharyya distance , 2003, Pattern Recognit..

[20]  P. Réfrégier,et al.  Bhattacharyya distance as a contrast parameter for statistical processing of noisy optical images. , 2004, Journal of the Optical Society of America. A, Optics, image science, and vision.

[21]  Kunihiko Fukushima,et al.  Neocognitron: A Self-Organizing Neural Network Model for a Mechanism of Visual Pattern Recognition , 1982 .

[22]  Max Welling,et al.  Auto-Encoding Variational Bayes , 2013, ICLR.

[23]  Yann Ollivier,et al.  Layer-wise learning of deep generative models , 2012, ArXiv.

[24]  Guigang Zhang,et al.  Deep Learning , 2016, Int. J. Semantic Comput..

[25]  Alex Krizhevsky,et al.  Learning Multiple Layers of Features from Tiny Images , 2009 .

[26]  James D. Keeler,et al.  Layered Neural Networks with Gaussian Hidden Units as Universal Approximations , 1990, Neural Computation.

[27]  Yann LeCun,et al.  Generalization and network design strategies , 1989 .

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

[29]  Michael I. Jordan,et al.  Distance Metric Learning with Application to Clustering with Side-Information , 2002, NIPS.