# Fast offset corrected in-memory training

Source: [Fast offset corrected in-memory training](<https://www.sota2.com/research/paper/68fa748f1e209131cea627c4>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-26T03:12:36.753Z

Authors: Malte J. Rasch, Fabio Carta, Omebayode Fagbohungbe, Tayfun Gokmen

Published: 2023-03-08T17:07:09.000Z

## Abstract

In-memory computing with resistive crossbar arrays has been suggested to accelerate deep-learning workloads in highly efficient manner. To unleash the full potential of in-memory computing, it is desirable to accelerate the training as well as inference for large deep neural networks (DNNs). In the past, specialized in-memory training algorithms have been proposed that not only accelerate the forward and backward passes, but also establish tricks to update the weight in-memory and in parallel. However, the state-of-the-art algorithm (Tiki-Taka version 2 (TTv2)) still requires near perfect offset correction and suffers from potential biases that might occur due to programming and estimation inaccuracies, as well as longer-term instabilities of the device materials. Here we propose and describe two new and improved algorithms for in-memory computing (Chopped-TTv2 (c-TTv2) and Analog Gradient Accumulation with Dynamic reference (AGAD)), that retain the same runtime complexity but correct for any remaining offsets using choppers. These algorithms greatly relax the device requirements and thus expanding the scope of possible materials potentially employed for such fast in-memory DNN training.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Image Classification on reduced-scale ImageNet-1K (test)](<https://www.sota2.com/research/sota/image-classification-on-reduced-scale-imagenet-1k-test.md>): Image Classification; reduced-scale ImageNet-1K (test); Top-1 Accuracy: 64.09.

- [Image Classification on MNIST (test) (Accuracy Only)](<https://www.sota2.com/research/sota/image-classification-on-mnist-test-accuracy-only.md>): Image Classification; MNIST (test); Accuracy: 92.88.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2303.04721>)

[PDF](<https://arxiv.org/pdf/2303.04721.pdf>)