Abstract

Neural networks in the brain and artificial neural networks (ANNs) in silico are both able to learn complex functionality. While each artificial neuron is updated based on global information, using a central processor (CPU) and memory, each real neuron in the brain updates itself without external CPU . In this talk I will describe the first laboratory realization of such self-learning without use of CPU or memory.  Our systems consist of a network of identical variable-resistive elements that self-adjust using a local rule based on the voltage drops they experience under contrastive boundary conditions. As such, they have many brain-like advantages over ANNs and enable study of learning as a bottom-up emergent process. Co-authors: Sam Dillavou, Menachem Stern, Jacob Wycoff, Ben Beyer, Marc Miskin, Andrea Liu