Loading [MathJax]/extensions/TeX/ietmacros.js
7.5nJ/inference CMOS Echo State Network for Coronary Heart Disease prediction | IEEE Conference Publication | IEEE Xplore

7.5nJ/inference CMOS Echo State Network for Coronary Heart Disease prediction

Publisher: IEEE

Abstract:

This work presents the first on-chip, mixed-signal echo state network (ESN) for early prediction of heart disease. The ESN comprises an input layer, a non-linear projecti...View more

Abstract:

This work presents the first on-chip, mixed-signal echo state network (ESN) for early prediction of heart disease. The ESN comprises an input layer, a non-linear projection (NP) layer, and an output layer. Only the output layer of the ESN requires training. The input layer weights are time-invariant and drawn from a static binary random distribution. Thus, the proposed ESN has significantly lower trainable parameters compared to other non-linear neural networks used for similar prediction tasks. A 65nm prototype is validated with the Cleveland Heart Disease (CHD) dataset. The ESN achieves a mean accuracy of 84.6% over 5 test chips while consuming 7.5nJ energy/inference.
Date of Conference: 13-22 September 2021
Date Added to IEEE Xplore: 26 October 2021
ISBN Information:
Publisher: IEEE
Conference Location: Grenoble, France

Funding Agency:


References

References is not available for this document.