Zubia Mansoor

Title: Exploring Out of Distribution: Deep Neural Networks and the Human Brain
Date: August 17, 2021
Time: 10:30 am (PDT)
Location: Remote delivery

Abstract

Deep neural networks have achieved state-of-the-art performance across a wide range of tasks. Convolutional neural networks, with their ability to learn complex spatial features, have surpassed human-level accuracy on many image classification problems. These architectures are however still often unable to make accurate predictions when the test data distribution differs from that of the training data. In contrast, humans naturally excel at such out-of-distribution generalizations. Novel solutions have been developed to improve a deep neural net's ability to handle out-of-distribution data. The advent of methods such as Push-Pull and AugMix have improved model robustness and generalization. We are interested in assessing whether or not such models achieve the most human-like generalization across a wide variety of image classification tasks. The identification of such models could shed light on human cognition and the analogy between neural nets and the human brain.

Keywords: Out-of-distribution, deep learning, convolutional neural networks, cognitive science