Neuromorphic Kalman filter implementation in IBM's TrueNorth

2Citations
Citations of this article
10Readers
Mendeley users who have this article in their library.

This article is free to access.

Abstract

Following the advent of a post-Moore's law field of computation, novel architectures continue to emerge. With composite, multi-million connection neuromorphic chips like IBM's TrueNorth, neural engineering has now become a feasible technology in this novel computing paradigm. High Energy Physics experiments are continuously exploring new methods of computation and data handling, including neuromorphic, to support the growing challenges of the field and be prepared for future commodity computing trends. This work details the first instance of a Kalman filter implementation in IBM's neuromorphic architecture, TrueNorth, for both parallel and serial spike trains. The implementation is tested on multiple simulated systems and its performance is evaluated with respect to an equivalent non-spiking Kalman filter. The limits of the implementation are explored whilst varying the size of weight and threshold registers, the number of spikes used to encode a state, size of neuron block for spatial encoding, and neuron potential reset schemes.

Cite

CITATION STYLE

APA

Carney, R., Bouchard, K., Calafiura, P., Clark, D., Donofrio, D., Garcia-Sciveres, M., & Livezey, J. (2017). Neuromorphic Kalman filter implementation in IBM’s TrueNorth. In Journal of Physics: Conference Series (Vol. 898). Institute of Physics Publishing. https://doi.org/10.1088/1742-6596/898/4/042021

Register to see more suggestions

Mendeley helps you to discover research relevant for your work.

Already have an account?

Save time finding and organizing research with Mendeley

Sign up for free