Artificial neural manifolds
TL;DR
An artificial neural manifold based on Mott memristors is constructed, enabling accurate and robust prediction while reducing the number of required samples, and a memory factor is introduced to modify the STI equation, which improves prediction accuracy and robustness.
Abstract
The brain can rapidly perform perception, prediction, and decision-making tasks. The capabilities stem from the collective coordination of neurons. This collective activity forms a manifold structure that naturally supports information representation and prediction, yet most neuromorphic work ignores this structure. Here, we construct an artificial neural manifold based on Mott memristors, enabling accurate and robust prediction while reducing the number of required samples. By constructing an artificial neuron circuit, a bell-shaped tuning curve similar to that of biological neurons is obtained. The tuning curve converges the large-scale neuronal firing into a compact, low-dimensional manifold structure. This structure satisfies the delay embedding theorem to establish a spatiotemporal information (STI) equation, enabling rapid prediction of neural activity with small sample sizes. In addition, we introduce a memory factor to modify the STI equation, which improves prediction accuracy and robustness. We not only accurately perceive incomplete images but also predict epileptic seizures. Inspired by collective neuronal activity, Wang et al. develop a Mott-memristor-based hardware system that maps complex spike signals to population-level artificial neural dynamics, enabling accurate prediction from limited data.