Speaker:

Kenneth Kurtz, Associate Professor of Psychology, Binghamton University, USA

Title:

The Divergent Autoencoder as a Machine Learning Classifier

Location:

Owheo G34 - 1:00 pm, Friday 24 March

Abstract:

The Divergent Autoencoder (Kurtz, 2007, 2015) combines aspects of generative and discriminative methods by directly applying reconstructive learning toward a classification task. This differs from the approach of learning a task-neutral generative model to provide item representations for a discriminative classifier. The core design principle is the use of separate channels of output nodes each dedicated to autoassociative learning of the members of one class - with a hidden layer shared by all channels. Classification likelihood depends on reconstructive success. I will focus on: (1) formal and informal characterizations of divergent autoencoder behavior and performance; and (2) how the approach is extensible in terms of architecture (e.g., number of hidden layers) and task (e.g., unsupervised learning, regression, co-learning).