Next was an interesting talk by Debaditya Roy on predicting human behavior at #IITHyderabad. Roy nicely gets into the importance of assessing goals to accurately interpreting behavioral #data to predict behavior https://www.youtube.com/live/mtuqGcF6IGQ?feature=share&t=6484 (11/12) #MachineLearning

Next was an interesting talk by Srijith P.K. on continual #DeepLearning at #IITHyderabad. Catastrophic forgetting is a frustratingly persistent problem in deep learning, and the approach presented here seems to make nice progress in allowing for more continuous learning in these models https://www.youtube.com/live/59Ke-q7iL88?feature=share&t=72 (5/7) #AI #MachineLearning

Next was a nice talk by Vineeth N Balasubramanian on causality in explainable #AI at #IITHyderabad. After a summary of #ExplainableAI, Balasubramanian shows some promising methods that can tease out causal relationships under certain conditions https://www.youtube.com/live/XNaxJXzkJss?feature=share&t=2978 (7/9)

Next was an intriguing talk by Ole-Christoffer Granmo on the Tsetlin machine approach to #AI at #IITHyderabad. This is classic AI methods brought into the modern world, which provides a nice contrast to the data and compute intensive techniques currently en vogue https://www.youtube.com/watch?v=x-5kKVRiIV4 (3/7)

First was a nice talk by @tw on the potential of and concerns with generative #AI at #IITHyderabad. This is one of the better summaries of generative AI that I've heard, and especially with the recent hype around #ChatGPT the grounded discussion here is much appreciated https://www.youtube.com/watch?v=zTLMC6RoqsM (2/6)