Schuessler, F; Mastrogiuseppe, F; Dubreuil, A; Ostojic, S; Barak, O; (2020) The interplay between randomness and structure during learning in RNNs. In: Larochelle, Hugo and Ranzato, Marc'Aurelio and Hadsell, Raia and Balcan, Maria-Florina and Lin, Hsuan-Tien, (eds.) Advances in Neural Information Processing Systems 33 (NeurIPS 2020). NeurIPS

Preview

Text NeurIPS-2020-the-interplay-between-randomness-and-structure-during-learning-in-rnns-Paper.pdf - Published Version Download (484kB) | Preview

Abstract

Recurrent neural networks (RNNs) trained on low-dimensional tasks have been widely used to model functional biological networks. However, the solutions found by learning and the effect of initial connectivity are not well understood. Here, we examine RNNs trained using gradient descent on different tasks inspired by the neuroscience literature. We find that the changes in recurrent connectivity can be described by low-rank matrices, despite the unconstrained nature of the learning algorithm. To identify the origin of the low-rank structure, we turn to an analytically tractable setting: training a linear RNN on a simplified task. We show how the low-dimensional task structure leads to low-rank changes to connectivity. This low-rank structure allows us to explain and quantify the phenomenon of accelerated learning in the presence of random initial connectivity. Altogether, our study opens a new perspective to understanding trained RNNs in terms of both the learning process and the resulting network structure.

Download activity - last month

Export as XMLJSONCSV

Download activity - last 12 months

Export as XMLJSONCSV

Downloads by country - last 12 months

Export as CSVJSONXML

Archive Staff Only

View Item