Memristor-CMOS Hybrid Circuit for Temporal-Pooling of Sensory and Hippocampal Responses of Cortical Neurons.

Tien Nguyen,Khoa Pham,Kyeong-Sik Min

doi:10.3390/ma12060875

Abstract

As a software framework, Hierarchical Temporal Memory (HTM) has been developed to perform the brain’s neocortical functions, such as spatial and temporal pooling. However, it should be realized with hardware not software not only to mimic the neocortical function but also to exploit its architectural benefit. To do so, we propose a new memristor-CMOS (Complementary Metal-Oxide-Semiconductor) hybrid circuit of temporal-pooling here, which is composed of the input-layer and output-layer neurons mimicking the neocortex. In the hybrid circuit, the input-layer neurons have the proximal and basal/distal dendrites to combine sensory information with the temporal/location information from the brain’s hippocampus. Using the same crossbar architecture, the output-layer neurons can perform a prediction by integrating the temporal information on the basal/distal dendrites. For training the proposed circuit, we used only simple Hebbian learning, not the complicated backpropagation algorithm. Due to the simple hardware of Hebbian learning, the proposed hybrid circuit can be very suitable to online learning. The proposed memristor-CMOS hybrid circuit has been verified by the circuit simulation using the real memristor model. The proposed circuit has been verified to predict both the ordinal and out-of-order sequences. In addition, the proposed circuit has been tested with the external noise and memristance variation.

Highlights

The neocortex occupying most of the brain’s surface area has been believed to perform the most human-like functions such as intelligence, cognition, etc. among all human organs
To spatial pooling with hardware, we developed the spatial-pooling memristor crossbar circuit in a realize the spatial pooling with hardware, we developed the spatial-pooling memristor crossbar previous work, where the work, circuit could theconvert sensory information to the that circuit in a previous where the convert circuit could the sensory information to the thatmeant the representation neurons meant of thecortical representation of cortical
[30]. dendrites to combine the sensory information by hardware not software, in thiscomposed paper, we propose new memristorwith the temporal/location information

Summary

Introduction

The neocortex occupying most of the brain’s surface area has been believed to perform the most human-like functions such as intelligence, cognition, etc. among all human organs. It is just 2.5-mm thick and is composed of six layers [1,2,3]. All six neocortical layers have the same columnar architecture, where the neocortical neurons are connected in both the vertical and horizontal directions to form various feedback and feedforward paths to communicate with each other. Anatomical experiments have observed the columnar architecture consistently through the entire neocortex [4,5]. This fact may hint that there is a canonical neural circuitry that can describe various neocortical functions with one model [6]. We try to develop a memristor-CMOS hybrid circuit that can emulate the neocortex’s canonical neural circuitry by combining nanoscale memristor crossbars with CMOS peripheral circuits

Methods

Results

Conclusion