Backpropagation for energy-efficient neuromorphic computing
Steven K. Esser, Rathinakumar Appuswamy, et al.
NeurIPS 2015
We present an approach to design spiking silicon neurons based on dynamical systems theory. Dynamical systems theory aids in choosing the appropriate level of abstraction, prescribing a neuron model with the desired dynamics while maintaining simplicity. Further, we provide a procedure to transform the prescribed equations into subthreshold current-mode circuits. We present a circuit design example, a positive-feedback integrate-and-fire neuron, fabricated in 0.25-μm CMOS. We analyze and characterize the circuit, and demonstrate that it can be configured to exhibit desired behaviors, including spikefrequency adaptation and two forms of bursting. © 2011 IEEE.
Steven K. Esser, Rathinakumar Appuswamy, et al.
NeurIPS 2015
Ben Varkey Benjamin, Peiran Gao, et al.
Proceedings of the IEEE
Filipp Akopyan, Jun Sawada, et al.
IEEE TCADIS
Bruno U. Pedroni, Srinjoy Das, et al.
IEEE TBioCAS