Design and Analysis of a Neuromemristive Reservoir Computing Architecture for Biosignal Processing

Abstract

Reservoir computing (RC) is gaining traction in several signal processing domains, owing to its non-linear stateful computation, spatiotemporal encoding, and reduced training complexity over recurrent neural networks (RNNs). Previous studies have shown the effectiveness of software-based RCs for a wide spectrum of applications. A parallel body of work indicates that realizing RNN architectures using custom integrated circuits and reconfigurable hardware platforms yields significant improvements in power and latency. In this research, we propose a neuromemristive RC architecture, with doubly twisted toroidal structure, that is validated for biosignal processing applications. We exploit the device mismatch to implement the random weight distributions within the reservoir and propose mixed-signal subthreshold circuits for energy efficiency. A comprehensive analysis is performed to compare the efficiency of the neuromemristive RC architecture in both digital(reconfigurable) and subthreshold mixed-signal realizations. Both Electroencephalogram (EEG) and Electromyogram (EMG) biosignal benchmarks are used for validating the RC designs. The proposed RC architecture demonstrated an accuracy of 90 and 84% for epileptic seizure detection and EMG prosthetic finger control, respectively.

Keywords: EMG signal processing; epileptic seizure detection and prediction; memristors; neuromemristive systems; neuromorphic; neuromorphic hardware; process variations; reservoir computing.

Figure 1

(A) Echo State Network consists of three layers: input layer, reservoir layer, and output layer. (B) Echo State Network abstract structure. How signals propagate through the ESN and the effects of different weight sets in the network.

Figure 2

(A) ESN with ring reservoir topology. Each reservoir neuron has two inputs and one output. (B) ESN with center neuron topology. Reservoir neurons are connected to one center neuron that works as a hub. (C) ESN with hybrid topology. Each neuron has three inputs and one output.

Figure 3

(A) Hybrid topology implemented as four rings. The rings are color coded based on Figure 2. Purple ring is used for the connections between the input layer and the reservoir layer. Green ring is used for the ring topology connections. Red ring is used for the center neuron connections. Orange ring is used for the connections between the reservoir layer and the output layer. (B) 5 x 5 doubly twisted toroidal network used to implement a 25 neurons hybrid reservoir. Dual links are used in this toroidal architecture to implement the four ring connection patterns required for the hybrid reservoir topology. The internal structure of each node in utilized toroidal architecture is shown. Each node contains a reservoir neuron along with all associated synaptic links.

Figure 4

RTL level diagram of a reservoir neuron in the digital ESN implementation. All directions of signals are from left to right.

Figure 5

(A) Hyperbolic tangent neuron circuit and (B) its current-voltage relationship.

Figure 6

Schematic of (A) a deterministic current-mode constant weight synapse circuit and (B) the proposed synapse circuit that leverages process variations.

Figure 7

Monte Carlo analyses showing the distributions of (A) random weights and (B) random biases associated with the synapse design in Figure 6B.

Figure 8

Mean areas vs. the weight resolution for the baseline and proposed synapses circuits in Figure 6 where the baseline design was distributed (A) uniformly between −1 and +1, (B) normally with 0 mean and std = 0.1, and (C) lognormally with 0 mean and std = 2.85. In each case, the proposed synapse design's maximum area (6A_match) is shown as a reference.

Figure 9

Readout circuit for a single ESN output. A memristor crossbar provides trainable weights to the linear output neuron.

Figure 10

Epileptic seizure detection accuracy vs.the reservoir size and alpha for (A) Ring topology with maximum accuracy of 86% and (B) Hybrid topology with maximum accuracy of 90%.

Figure 11

The effects of the number of neurons within the reservoir and alpha on the testing accuracy of finger motion recognition using hybrid topology.

Figure 12

Confusion matrix of finger classification from surface EMG signals using 300 neurons hybrid reservoir for (A) training with accuracy of 87% and (B) testing with accuracy of 84%.

Figure 13

Kernel results vs. different reservoir sizes for hybrid topology reservoir testing (A) EEG and (B) EMG signals. The boxes represent the 25th and 75th percentiles of the measurements. The whiskers represents values out of this 25–75th percentiles. Since the percentiles range is centered in (B), the sizes of the boxes in (B) are very small (just a line that represent the mean of the range).

Figure 14

Lyapunov's exponent results vs. different reservoir sizes for hybrid topology reservoir testing (A) EEG and (B) EMG signals. The boxes represent the 25th and 75th percentiles of the measurements. The whiskers represent values outside the 25–75th percentiles.

Figure 15

Power consumption vs. reservoir size of four ESN topologies: one way ring, two way ring, hybrid, and random on log scale plot. The one way ring topology has lower power consumption compared to the other topologies while the random topology has higher power consumption compared to the other topologies.