Biological neural networks demonstrate complex memory and plasticity functions. This work proposes a single memristor based on SrTiO3 that emulates six synaptic functions for energy efficient operation. The bio-inspired deep neural network is trained to play Atari Pong, a complex reinforcement learning task in a dynamic environment.
Single neuromorphic memristor closely emulates multiple synaptic mechanisms for energy efficient neural networks
Posted in biological, robotics/AI