Skip to contentSkip to filters

We use cookies for analytics.

On continual learning with gradient descent for neural networks

Arya Mazumdar

UC San Diego

Recording

1 h

Abstract

Arya Mazumdar studies forgetting in one-hidden-layer quadratic networks trained by gradient descent on sequential noisy XOR classification tasks with orthogonal cluster means. The analysis bounds train- and test-time forgetting as the sample size, update count, width and number of tasks change. Numerical experiments probe how the relationships carry over beyond the analyzed setting.

Topics