Ensemble perspective for understanding temporal credit assignment

TL;DR

This paper introduces a novel ensemble-based approach using spike and slab distributions to understand and improve temporal credit assignment in recurrent neural networks, revealing neural selectivity and the impact of weight uncertainty.

Contribution

It proposes a spike and slab distribution model for recurrent connections and derives a mean-field algorithm for ensemble training, offering mechanistic insights into temporal credit assignment.

Findings

Identifies key connections influencing network performance

Shows how hyperparameters affect spatio-temporal information processing

Reveals emergent neural selectivity patterns

Abstract

Recurrent neural networks are widely used for modeling spatio-temporal sequences in both nature language processing and neural population dynamics. However, understanding the temporal credit assignment is hard. Here, we propose that each individual connection in the recurrent computation is modeled by a spike and slab distribution, rather than a precise weight value. We then derive the mean-field algorithm to train the network at the ensemble level. The method is then applied to classify handwritten digits when pixels are read in sequence, and to the multisensory integration task that is a fundamental cognitive function of animals. Our model reveals important connections that determine the overall performance of the network. The model also shows how spatio-temporal information is processed through the hyperparameters of the distribution, and moreover reveals distinct types of emergent neural selectivity. To provide a mechanistic analysis of the ensemble learning, we first derive an analytic solution of the learning at the infinitely-large-network limit. We then carry out a low-dimensional projection of both neural and synaptic dynamics, analyze symmetry breaking in the parameter space, and finally demonstrate the role of stochastic plasticity in the recurrent computation. Therefore, our study sheds light on mechanisms of how weight uncertainty impacts the temporal credit assignment in recurrent neural networks from the ensemble perspective.