paper-with-me

홈 › Papers

Bespoke Approximation of Multiplication-Accumulation and Activation Targeting Printed Multilayer Perceptrons

2023-12-29 · Florentia Afentaki, Gurol Saglam, Argyris Kokkinis, Kostas Siozios, Georgios Zervakis, Mehdi B Tahoori

Printed Electronics (PE) feature distinct and remarkable characteristics that make them a prominent technology for achieving true ubiquitous computing. This is particularly relevant in application domains that require conformal and ultra-low cost solutions, which have experienced limited penetration of computing until now. Unlike silicon-based technologies, PE offer unparalleled features such as non-recurring engineering costs, ultra-low manufacturing cost, and on-demand fabrication of conformal, flexible, non-toxic, and stretchable hardware. However, PE face certain limitations due to their large feature sizes, that impede the realization of complex circuits, such as machine learning classifiers. In this work, we address these limitations by leveraging the principles of Approximate Computing and Bespoke (fully-customized) design. We propose an automated framework for designing ultra-low power Multilayer Perceptron (MLP) classifiers which employs, for the first time, a holistic approach to approximate all functions of the MLP's neurons: multiplication, accumulation, and activation. Through comprehensive evaluation across various MLPs of varying size, our framework demonstrates the ability to enable battery-powered operation of even the most intricate MLP architecture examined, significantly surpassing the current state of the art.

📄 PDF Abstract BibTeX arXiv:2312.17612

Code (1)

floAfentaki/Approximation-Techniques-Targeting-Printed-MLPs 공식 구현 tf

Similar Papers 제목 키워드 기반

SHE: A Fast and Accurate Deep Neural Network for Encrypted Data

2019-06-01 · NeurIPS 2019 12 · Qian Lou, Lei Jiang

Homomorphic Encryption (HE) is one of the most promising security solutions to emerging Machine Learning as a Service (MLaaS). Leveled-HE (LHE)-enabled Convolutional Neural Networks (LHECNNs) are proposed to implement ML…

Quantization

Cross-Layer Approximation For Printed Machine Learning Circuits

2022-03-11 · Giorgos Armeniakos, Georgios Zervakis, Dimitrios Soudris, Mehdi B. Tahoori 외

Printed electronics (PE) feature low non-recurring engineering costs and low per unit-area fabrication costs, enabling thus extremely low-cost and on-demand hardware. Such low-cost fabrication allows for high customizati…

BIG-bench Machine Learning

WrapNet: Neural Net Inference with Ultra-Low-Precision Arithmetic

2021-01-01 · ICLR 2021 1 · Renkun Ni, Hong-Min Chu, Oscar Castaneda, Ping-Yeh Chiang 외

Low-precision neural networks represent both weights and activations with few bits, drastically reducing the multiplication complexity. Nonetheless, these products are accumulated using high-precision (typically 32-bit) …

Quantization

WrapNet: Neural Net Inference with Ultra-Low-Resolution Arithmetic

2020-07-26 · Renkun Ni, Hong-Min Chu, Oscar Castañeda, Ping-Yeh Chiang 외

Low-resolution neural networks represent both weights and activations with few bits, drastically reducing the multiplication complexity. Nonetheless, these products are accumulated using high-resolution (typically 32-bit…

Quantization

High-Rate Quantized Matrix Multiplication I

2026-01-23 · Or Ordentlich, Yury Polyanskiy arxiv

This paper investigates the problem of quantized matrix multiplication (MatMul), which has become crucial for the efficient deployment of large language models (LLMs). We consider a Generic MatMul setting, where both mat…