A new inference approach for training shallow and deep generalized linear models of noisy interacting neurons

TL;DR

This paper introduces a two-step inference method for training generalized linear models of neuronal activity that improves stability, robustness, and generalization across complex stimuli, and extends to deep neural networks.

Contribution

The paper presents a novel two-step inference approach that separates stimulus effects from network interactions, enhancing model robustness and generalization for neuronal data.

Findings

Improved model stability and performance on retinal ganglion cell data.

Models generalize well across diverse visual stimuli.

Extension of the method to deep convolutional neural networks.

Abstract

Generalized linear models are one of the most efficient paradigms for predicting the correlated stochastic activity of neuronal networks in response to external stimuli, with applications in many brain areas. However, when dealing with complex stimuli, the inferred coupling parameters often do not generalize across different stimulus statistics, leading to degraded performance and blowup instabilities. Here, we develop a two-step inference strategy that allows us to train robust generalized linear models of interacting neurons, by explicitly separating the effects of correlations in the stimulus from network interactions in each training step. Applying this approach to the responses of retinal ganglion cells to complex visual stimuli, we show that, compared to classical methods, the models trained in this way exhibit improved performance, are more stable, yield robust interaction networks, and generalize well across complex visual statistics. The method can be extended to deep convolutional neural networks, leading to models with high predictive accuracy for both the neuron firing rates and their correlations.