Silicon neurons that compute

Authors:
Swadesh Choudhary;Steven Sloan;Sam Fok;Alexander Neckar;Eric Trautmann;Peiran Gao;Terry Stewart;Chris Eliasmith;Kwabena Boahen
Affiliations:
Stanford University, Stanford, CA;Stanford University, Stanford, CA;Stanford University, Stanford, CA;Stanford University, Stanford, CA;Stanford University, Stanford, CA;Stanford University, Stanford, CA;Stanford University, Stanford, CA;Stanford University, Stanford, CA;Stanford University, Stanford, CA
Venue:
ICANN'12 Proceedings of the 22nd international conference on Artificial Neural Networks and Machine Learning - Volume Part I
Year:
2012

Citing 3
Cited 4

Translinear circuits in subthreshold MOS

Analog Integrated Circuits and Signal Processing - Special issue: translinear circuits
Neural Engineering (Computational Neuroscience Series): Computational, Representation, and Dynamics in Neurobiological Systems

Neural Engineering (Computational Neuroscience Series): Computational, Representation, and Dynamics in Neurobiological Systems
Synchrony in Silicon: The Gamma Rhythm

IEEE Transactions on Neural Networks

2013 Special Issue: Design of silicon brains in the nano-CMOS era: Spiking neurons, learning synapses and neural architecture optimization

Neural Networks
2013 Special Issue: Learning the pseudoinverse solution to network weights

Neural Networks
2013 Special Issue: Computing with networks of spiking neurons on a biophysically motivated floating-gate based neuromorphic integrated circuit

Neural Networks
Spatio-temporal spike pattern classification in neuromorphic systems

Living Machines'13 Proceedings of the Second international conference on Biomimetic and Biohybrid Systems

Quantified Score

Hi-index	0.00

Visualization

Abstract

We use neuromorphic chips to perform arbitrary mathematical computations for the first time. Static and dynamic computations are realized with heterogeneous spiking silicon neurons by programming their weighted connections. Using 4K neurons with 16M feed-forward or recurrent synaptic connections, formed by 256K local arbors, we communicate a scalar stimulus, quadratically transform its value, and compute its time integral. Our approach provides a promising alternative for extremely power-constrained embedded controllers, such as fully implantable neuroprosthetic decoders.