Machine Learning with Memristors via Thermodynamic RAM

TL;DR

This paper introduces Thermodynamic RAM (kT-RAM), a neuromemristive co-processor based on AHaH computing, leveraging memristors for efficient, nature-inspired machine learning operations integrated with digital systems.

Contribution

It presents a memristor technology for kT-RAM enabling bi-directional conductance adaptation with low-voltage pulses, advancing neuromemristive computing architectures.

Findings

kT-RAM can perform unsupervised feature learning, classification, and anomaly detection.

Memristor conductance can be incrementally adapted with 1V, 1μs pulses.

The architecture surpasses traditional CPU, GPU, and FPGA performance in synaptic operations.

Abstract

Thermodynamic RAM (kT-RAM) is a neuromemristive co-processor design based on the theory of AHaH Computing and implemented via CMOS and memristors. The co-processor is a 2-D array of differential memristor pairs (synapses) that can be selectively coupled together (neurons) via the digital bit addressing of the underlying CMOS RAM circuitry. The chip is designed to plug into existing digital computers and be interacted with via a simple instruction set. Anti-Hebbian and Hebbian (AHaH) computing forms the theoretical framework from which a nature-inspired type of computing architecture is built where, unlike von Neumann architectures, memory and processor are physically combined for synaptic operations. Through exploitation of AHaH attractor states, memristor-based circuits converge to attractor basins that represents machine learning solutions such as unsupervised feature learning, supervised classification and anomaly detection. Because kT-RAM eliminates the need to shuttle bits back and forth between memory and processor and can operate at very low voltage levels, it can significantly surpass CPU, GPU, and FPGA performance for synaptic integration and learning operations. Here, we present a memristor technology developed for use in kT-RAM, in particular bi-directional incremental adaptation of conductance via short low-voltage 1.0 V, 1.0 microsecond pulses.