Memristive Reservoir Computing Architecture for Epileptic Seizure Detection

被引：31

作者：

Merkel, Cory ^{[1
]}

Saleh, Qutaiba ^{[1
]}

Donahue, Colin ^{[1
]}

Kudithipudi, Dhireesha ^{[1
]}

机构：

[1] Rochester Inst Technol, NanoComp Res Lab, Rochester, NY 14623 USA

来源：

5TH ANNUAL INTERNATIONAL CONFERENCE ON BIOLOGICALLY INSPIRED COGNITIVE ARCHITECTURES, 2014 BICA | 2014年 / 41卷

基金：

美国国家科学基金会;

关键词：

Reservoir Computing; Echo State Networks; Memristors; Epilepsy Seizure; Seizure detection; STATE;

D O I：

10.1016/j.procs.2014.11.110

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

Echo state networks (ESN) or reservoirs, are random, recurrent neural network topologies that integrate temporal data over short time windows by operating on the edge of chaos. Recently, there is a significant effort on the mathematical modeling and software topologies of the reservoirs. However, hardware reservoir fabrics are essential to deploy in energy constrained environments. In this paper, we investigate a hardware reservoir with bi-stable memristive synapses. In particular, we demonstrate a scalable hardware model for detecting real-time epileptic seizures in human models. The performance of the proposed reservoir hardware is evaluated for absent seizure signals with 85% accuracy.

引用

页码：249 / 254

页数：6