Firing Rate Neural Network Implementations of Model Predictive Control

TL;DR

This paper translates model predictive control into firing rate neural networks, providing insights into neural dynamics for planning and demonstrating sparse neural networks can effectively perform MPC.

Contribution

It introduces a method to implement MPC in neural networks using the projected gradient approach and explores biologically plausible sparse network configurations.

Findings

Sparse neural networks can perform MPC effectively.

The approach offers insights into neural dynamics underlying planning.

Numerical simulations validate the neural network implementations.

Abstract

Human and animal brains perform planning to enable complex movements and behaviors. This process can be effectively described using model predictive control (MPC); that is, brains can be thought of as implementing some version of MPC. How is this done? In this work, we translate model predictive controllers into firing rate neural networks, offering insights into the nonlinear neural dynamics that underpin planning. This is done by first applying the projected gradient method to the dual problem, then generating alternative networks through factorization and contraction analysis. This allows us to explore many biologically plausible implementations of MPC. We present a series of numerical simulations to study different neural networks performing MPC to balance an inverted pendulum on a cart (i.e., balancing a stick on a hand). We illustrate that sparse neural networks can effectively implement MPC; this observation aligns with the sparse nature of the brain.