← Search

Arulmurugan Ambikapathi

3 accepted papers

2022

Investigating Robustness of Biological vs. Backprop Based Learning

ICASSP 2022accepted

Robustness of learning algorithms remains an important problem to be solved from both the perspective of adversarial attacks and improving generalization. In this work, we investigate the robustness of biologically inspired Hebbian learning algorithm in depth. We find that Hebbian learning based alg…

Cited by 0SourceScholar
2022

Online Continual Learning Using Enhanced Random Vector Functional Link Networks

ICASSP 2022accepted

We propose an online continual learning algorithm based on an enhanced Random Vector Functional Link Network (OCL-eRVFL), that learns a sequence of tasks continually, where each task is defined by streaming data with each sample arriving once and only once. As data for a new task in domain increment…

Cited by 0SourceScholar
2021

HebbNet: A Simplified Hebbian Learning Framework to do Biologically Plausible Learning

ICASSP 2021accepted

Backpropagation has revolutionized neural network training however, its biological plausibility remains questionable. Hebbian learning, a completely unsupervised and feedback free learning technique is a strong contender for a biologically plausible alternative. However, so far, it has neither achie…

Cited by 0SourceScholar