Machine Intelligence Reading Group Discussion | Joseph KJ




Speaker
Joseph KJ  
CS Ph.D., IITH
Machine Intelligence group is glad to announce Reading Groups session with Joseph KJ (CS Ph.D.), as we discuss about his recent work on Meta-Consolidation for Continual Learning published in NeurIPS 2020.

Abstract:
The ability to continuously learn and adapt itself to new tasks, without losing grasp of already acquired knowledge is a hallmark of biological learning systems, which current deep learning systems fall short of. In this work, we present a novel methodology for continual learning called MERLIN: Meta-Consolidation for Continual Learning. We assume that the weights of a neural network, for solving tasks, come from a meta-distribution. This meta-distribution is learned and consolidated incrementally. We operate in the challenging online continual learning setting, where a data point is seen by the model only once. Our experiments with continual learning benchmarks of MNIST, CIFAR-10, CIFAR-100, and Mini-ImageNet datasets show consistent improvement over five baselines, including a recent state-of-the-art, corroborating the promise of MERLIN.

 Join the Talk on 7th Feb, Sunday 5 PM IST on Google Meet!