Date: Wed., Apr 20th 2022, 03:00 PM to 04:00 PM (MDT)
Presented by: Dr. Yani Ioannou, Assistant Professor, University of Calgary
Abstract: Machine learning requires assumptions and data, with the assumptions based on domain knowledge. With the exponential increase in dataset set and computation we’ve been able to reduce the domain expertise and inductive bias we integrate in computer vision models, from manually designed features such as SIFT, to learning representations with deep learning. Recently this approach has been pushed even further, with Convolutional Neural Networks (CNNs), integrating strong inductive bias in their structure, being replaced with Vision Transformers (ViT), or even fully-connected neural networks with alternative training regimes. In this talk, Dr. Yanni Ioannou, Assistant Professor at the University of Calgary, will discuss the current limits of this approach, and the need for more domain-agnostic learning.
Sponsored locally by the IEEE Southern Alberta Section (SAS) Computer Society (C16)