Timezone: »

 
Poster
A Probabilistic Framework for Deep Learning
Ankit Patel · Minh Nguyen · Richard Baraniuk

Wed Dec 07 09:00 AM -- 12:30 PM (PST) @ Area 5+6+7+8 #57 #None
in Wednesday Posters »

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.

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

Author Information

Ankit Patel (Baylor College of Medicine and Rice University)
Minh Nguyen (Rice University)
Richard Baraniuk (Rice University)

More from the Same Authors