Brain2Model Transfer: Training sensory and decision models with human neural activity as a teacher

TL;DR

This paper introduces Brain2Model Transfer Learning (B2M), a framework that uses human neural activity as a teacher to improve training of sensory and decision models, leading to faster convergence and higher accuracy.

Contribution

The paper presents novel B2M strategies that leverage human brain activity to enhance artificial neural network training, demonstrating improved efficiency and performance.

Findings

Student networks converge faster with brain-based transfer.

Networks achieve higher accuracy than training without brain data.

B2M is validated in decision-making and scene reconstruction tasks.

Abstract

Transfer learning enhances the training of novel sensory and decision models by employing rich feature representations from large, pre-trained teacher models. Cognitive neuroscience shows that the human brain creates low-dimensional, abstract representations for efficient sensorimotor coding. Importantly, the brain can learn these representations with significantly fewer data points and less computational power than artificial models require. We introduce Brain2Model Transfer Learning (B2M), a framework where neural activity from human sensory and decision-making tasks acts as the teacher model for training artificial neural networks. We propose two B2M strategies: (1) Brain Contrastive Transfer, which aligns brain activity and network activations through a contrastive objective; and (2) Brain Latent Transfer, which projects latent dynamics from similar cognitive tasks onto student networks via supervised regression of brain-derived features. We validate B2M in memory-based decision-making with a recurrent neural network and scene reconstruction for autonomous driving with a variational autoencoder. The results show that student networks benefiting from brain-based transfer converge faster and achieve higher predictive accuracy than networks trained in isolation. Our findings indicate that the brain's representations are valuable for artificial learners, paving the way for more efficient learning of complex decision-making representations, which would be costly or slow through purely artificial training.