Skip to yearly menu bar Skip to main content


A Probabilistic Framework for Deep Learning

Ankit Patel · Tan Nguyen · Richard Baraniuk

Area 5+6+7+8 #57

Keywords: [ Graphical Models ] [ Large Scale Learning and Big Data ] [ (Application) Object and Pattern Recognition ] [ Learning Theory ] [ Clustering ] [ Deep Learning or Neural Networks ]


We develop a probabilistic framework for deep learning based on the Deep Rendering Mixture Model (DRMM), a new generative probabilistic model that explicitly capture variations in data due to latent task nuisance variables. We demonstrate that max-sum inference in the DRMM yields an algorithm that exactly reproduces the operations in deep convolutional neural networks (DCNs), providing a first principles derivation. Our framework provides new insights into the successes and shortcomings of DCNs as well as a principled route to their improvement. DRMM training via the Expectation-Maximization (EM) algorithm is a powerful alternative to DCN back-propagation, and initial training results are promising. Classification based on the DRMM and other variants outperforms DCNs in supervised digit classification, training 2-3x faster while achieving similar accuracy. Moreover, the DRMM is applicable to semi-supervised and unsupervised learning tasks, achieving results that are state-of-the-art in several categories on the MNIST benchmark and comparable to state of the art on the CIFAR10 benchmark.

Live content is unavailable. Log in and register to view live content