Technical - Partner Event
AI Seminar – Amir Hossein Hosseini Akbarnejad
When
March 18, 2022 - March 18, 2022
12:00 PM – 1:00 PM MST
Where
Online
Online
Presenter: Amir Hossein Hosseini Akbarnejad, University of Alberta
Title: GPEX, A Framework For Interpreting Artificial Neural Networks
Abstract: Machine learning researchers have long noted a trade-off between interpretability and prediction performance. On the one hand, traditional models are often interpretable to humans but they cannot achieve high prediction performances. At the opposite end of the spectrum, deep models can achieve state-of-the-art performances in many tasks but their predictions are known to be uninterpretable to humans. We present a framework that shortens the gap between the two aforementioned groups of methods. Given an artificial neural network (ANN), our method finds a Gaussian process (GP) whose predictions almost match those of the ANN. As GPs are highly interpretable, we use the trained GP to explain the ANN’s decisions. The explanations provide intriguing insights about the ANNs’ decisions. We examine some of the known theoretical conditions under which an ANN is interpretable by GPs. Some of those theoretical conditions are too restrictive for modern architectures. However, we hypothesize that only a subset of those theoretical conditions are sufficient. We implement our framework as a publicly available tool called GPEX.
Bio: Amir Akbarnejad is a PhD student at the University of Alberta working under supervision of Nilanjan Ray. His research is about machine learning and computer vision, with focus on histopathology data.
The University of Alberta Artificial Intelligence (AI) Seminar is a weekly meeting where researchers (including students, developers, and professors) interested in AI can share their current research. Presenters include local speakers from the University of Alberta and industry as well as other institutions. The seminars discuss a wide range of topics related in any way to Artificial Intelligence, from foundational theoretical work to innovative applications of AI techniques to new fields and problems are of interest. Learn more at the AI Seminar website and by subscribing to the mailing list!
This event is co-hosted with Technology AB
Looking to build AI capacity? Need a speaker at your event?
