High precision tuning of state for memristive devices by adaptable variation-tolerant algorithm

By Fabien Alibart, Ligang Gao, B. Hoskins, Dmitri B. Strukov. Nanotechnology, 2011

531 citations recorded by the source corpus.

Using memristive properties common for titanium dioxide thin film devices, we designed a simple write algorithm to tune device conductance at a specific bias point to 1% relative accuracy (which is roughly equivalent to seven-bit precision) within its dynamic range even in the presence of large variations in switching behavior. The high precision state is nonvolatile and the results are likely to be sustained for nanoscale memristive devices because of the inherent filamentary nature of the resistive switching. The proposed functionality of memristive devices is especially attractive for analog computing with low precision data. As one representative example we demonstrate hybrid circuitry consisting of an integrated circuit summing amplifier and two memristive devices to perform the analog multiply-and-add (dot-product) computation, which is a typical bottleneck operation in information processing.

Subfields: Artificial Intelligence, Electrical and Electronic Engineering

View Paper: https://www.semanticscholar.org/paper/a12fc67fec8f0e3153c96fa39ec761e3d24b0f4f

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Electrical and Electronic Engineering

Citations in the corpus

Neuro-Inspired Computing With Emerging Nonvolatile Memorys (2018, background): “4(d) [83].”
PRIME: A Novel Processing-in-Memory Architecture for Neural Network Computation in ReRAM-Based Main Memory (2016, unknown): “Recent work has demonstrated 7-bit MLC ReRAM [31].”
Dot-product engine for neuromorphic computing: Programming 1T1M crossbar to accelerate matrix-vector multiplication (2016, methodology): “After the conversion, we use close-loop tuning scheme [16]to program memristors to the desired conductance values.”
A compute-in-memory chip based on resistive random-access memory (2022, unknown): “In contrast, we utilize the intrinsic analogue programmability of RRAM 42 to directly store high-precision weights and train the neural networks to tolerate the lower SNR.”
Memristor-Based Multilayer Neural Networks With Online Gradient Descent Training (2015, unknown): “The proposed memristor-based design should resolve the main obstacles of the above CMOS-based designs, and provide a compact nonvolatile [71] circuit.”
Implementation of multilayer perceptron network with highly uniform passive memristive crossbar circuits (2017, background): “G(1)± and G(2)± are the device conductances in the first and second crossbar circuits, with ± superscripts denoting a specific device of a differential pair, while I± are the currents flowing into the corresponding neurons.”
The future of electronics based on memristive systems (2018, background): “Such multilevel behaviour has been exploited by a number of researchers 62–64 , showing repeatable state control from 5 different conductance levels (over 2 bits) to over 64 levels (6 bits) for a single memristor.”