paper-with-me

홈 › Papers

Optimizing for In-memory Deep Learning with Emerging Memory Technology

2021-12-01 · Zhehui Wang, Tao Luo, Rick Siow Mong Goh, Wei zhang, Weng-Fai Wong

In-memory deep learning computes neural network models where they are stored, thus avoiding long distance communication between memory and computation units, resulting in considerable savings in energy and time. In-memory deep learning has already demonstrated orders of magnitude higher performance density and energy efficiency. The use of emerging memory technology promises to increase the gains in density, energy, and performance even further. However, emerging memory technology is intrinsically unstable, resulting in random fluctuations of data reads. This can translate to non-negligible accuracy loss, potentially nullifying the gains. In this paper, we propose three optimization techniques that can mathematically overcome the instability problem of emerging memory technology. They can improve the accuracy of the in-memory deep learning model while maximizing its energy efficiency. Experiments show that our solution can fully recover most models' state-of-the-art accuracy, and achieves at least an order of magnitude higher energy efficiency than the state-of-the-art.

📄 PDF Abstract BibTeX arXiv:2112.00324

Code (0)

등록된 구현이 없습니다.

Tasks

Deep Learning

Similar Papers 제목 키워드 기반

LLMET: Enabling Cross-Layer Evaluation of Emerging M3D Memories for Energy-Efficient LLM Serving

2026-07-29 · Ming-Yen Lee, Hanchen Yang, Faaiq Waqar, Harsono Simka 외 arxiv

The energy consumption of Large Language Model (LLM) serving is becoming a major system challenge as deployment scales, driven by hardware power and thermal constraints and rising electricity costs. A key contributor to …

In-Memory Resistive RAM Implementation of Binarized Neural Networks for Medical Applications

2020-06-20 · Bogdan Penkovsky, Marc Bocquet, Tifenn Hirtzlin, Jacques-Olivier Klein 외

The advent of deep learning has considerably accelerated machine learning development. The deployment of deep neural networks at the edge is however limited by their high memory and energy consumption requirements. With …

BIG-bench Machine Learning

Low-Rank Training of Deep Neural Networks for Emerging Memory Technology

2020-09-08 · Albert Gural, Phillip Nadeau, Mehul Tikekar, Boris Murmann

The recent success of neural networks for solving difficult decision tasks has incentivized incorporating smart decision making "at the edge." However, this work has traditionally focused on neural network inference, rat…

Computational EfficiencyDecision MakingFederated Learning

Memory Wall is not gone: A Critical Outlook on Memory Architecture in Digital Neuromorphic Computing

2026-04-09 · Amirreza Yousefzadeh, Sameed Sohail, Ana Lucia Varbanescu arxiv

The rapid advancement of neuromorphic technology aims to address the memory wall challenge inherent in conventional von Neumann architectures. This paper critically examines current digital neuromorphic processors and th…

Low Rank Training of Deep Neural Networks for Emerging Memory Technology

2019-09-25 · Albert Gural, Phillip Nadeau, Mehul Tikekar, Boris Murmann

The recent success of neural networks for solving difficult decision tasks has incentivized incorporating smart decision making "at the edge." However, this work has traditionally focused on neural network inference, rat…

Computational EfficiencyDecision MakingFederated LearningQuantization