How Much is Brain Data Worth for Machine Learning?

TL;DR

This paper develops a theoretical framework to quantify the value of neural brain data in enhancing machine learning performance, considering factors like data quantity, noise, and task-brain alignment.

Contribution

It introduces a mathematical model and scaling laws to evaluate when and how brain data improves machine learning models, including robustness and data collection strategies.

Findings

Derived performance scaling laws for models trained on brain and task data.

Quantified the relative value of brain samples based on task-brain alignment and noise levels.

Identified conditions where brain data significantly enhances robustness and learning efficiency.

Abstract

If a person can solve a task, can measuring their brain make it easier to train a model to solve that task too? Recent NeuroAI work suggests that supplementing task training with neural recordings can modestly improve model performance and robustness. However, it is unclear when there should be a benefit from using neural data and how much benefit to expect. We formulate this question mathematically, and begin to address it theoretically using a simple, analytically tractable linear gaussian model of task targets and neural recordings. For a multimodal estimator trained on both brain data and task labels, we derive scaling laws for how performance scales with the numbers of brain and task samples. From these laws we derive relative value and exchange rates between brain samples and task samples, quantifying how much extra task samples neural data is worth as a function of task-brain alignment, neural and task noise, latent dimension, and brain data sample size. We also analyze test distribution shift, to identify conditions where brain-regularized learning can produce substantial robustness gains through learned invariances. Finally, under a fixed collection budget, we characterize the regimes in which brain data is worth collecting. Our results provide a foundation for understanding how valuable brain data could be for improving machine learning.