Efficient Probabilistic Inference in Generic Neural Networks Trained with Non-Probabilistic Feedback

TL;DR

This paper demonstrates that generic neural networks trained with simple error-based learning can perform near-optimal probabilistic inference across various psychophysical tasks, developing efficient sparse coding strategies.

Contribution

It shows that probabilistic inference can emerge naturally in generic neural networks trained with simple learning rules, without task-specific architectures.

Findings

Networks perform near-optimally in nine psychophysical tasks.

Number of neurons grows sub-linearly with input size.

Networks develop a sparsity-based probabilistic population code.

Abstract

Animals perform near-optimal probabilistic inference in a wide range of psychophysical tasks. Probabilistic inference requires trial-to-trial representation of the uncertainties associated with task variables and subsequent use of this representation. Previous work has implemented such computations using neural networks with hand-crafted and task-dependent operations. We show that generic neural networks trained with a simple error-based learning rule perform near-optimal probabilistic inference in nine common psychophysical tasks. In a probabilistic categorization task, error-based learning in a generic network simultaneously explains a monkey's learning curve and the evolution of qualitative aspects of its choice behavior. In all tasks, the number of neurons required for a given level of performance grows sub-linearly with the input population size, a substantial improvement on previous implementations of probabilistic inference. The trained networks develop a novel sparsity-based probabilistic population code. Our results suggest that probabilistic inference emerges naturally in generic neural networks trained with error-based learning rules.