Neuromorphic Processing: A Unifying Tutorial
This is an incremental tutorial for researchers in neuromorphic computing, focusing on power-efficient processing nodes.
The paper presents a unifying tutorial that implements multiple neuromorphic processing elements using a systematic analog approach, showing it can synthesize multidimensional dynamical systems into analog circuitry with minimal effort.
All systolic or distributed neuromorphic architectures require power-efficient processing nodes. In this paper, a unifying tutorial is presented which implements multiple neuromorphic processing elements using a systematic analog approach including synapse, neuron and astrocyte models. It is shown that the proposed approach can successfully synthesize multidimensional dynamical systems into analog circuitry with minimum effort.