5 papers
Not Just After One: Sleep-Inspired Replay Prevents Catastrophic Forgetting After Sequential Tasks
Anthony Bazhenov, Jean Erik Delanois, Giri P. Krishnan
One of the critical limitations of artificial neural networks is their lack of ability to continually learn: training on new tasks often leads to interference and forgetting of the…
Context is All You Need
Jean Erik Delanois, Shruti Joshi, Ryan Golden +2
Artificial Neural Networks (ANNs) are increasingly deployed across diverse real-world settings, where they must operate under data distributions that differ from those seen during…
Slumbering to Precision: Enhancing Artificial Neural Network Calibration Through Sleep-like Processes
Jean Erik Delanois, Aditya Ahuja, Giri P. Krishnan +1
Artificial neural networks are often overconfident, undermining trust because their predicted probabilities do not match actual accuracy. Inspired by biological sleep and the role…
Toward Lifelong Learning in Equilibrium Propagation: Sleep-like and Awake Rehearsal for Enhanced Stability
Yoshimasa Kubo, Jean Erik Delanois, Maxim Bazhenov
Recurrent neural networks (RNNs) trained using Equilibrium Propagation (EP), a biologically plausible training algorithm, have demonstrated strong performance in various tasks such…
Unsupervised Replay Strategies for Continual Learning with Limited Data
Anthony Bazhenov, Pahan Dewasurendra, Giri P. Krishnan +1
Artificial neural networks (ANNs) show limited performance with scarce or imbalanced training data and face challenges with continuous learning, such as forgetting previously learn…