HTMA-Net: Towards Multiplication-Avoiding Neural Networks via Hadamard Transform and In-Memory Computing

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Hamdan, Emadeldeen, Cetin, Ahmet Enis
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866917146241531904
author Hamdan, Emadeldeen
Cetin, Ahmet Enis
author_facet Hamdan, Emadeldeen
Cetin, Ahmet Enis
contents Reducing the cost of multiplications is critical for efficient deep neural network deployment, especially in energy-constrained edge devices. In this work, we introduce HTMA-Net, a novel framework that integrates the Hadamard Transform (HT) with multiplication-avoiding (MA) SRAM-based in-memory computing to reduce arithmetic complexity while maintaining accuracy. Unlike prior methods that only target multiplications in convolutional layers or focus solely on in-memory acceleration, HTMA-Net selectively replaces intermediate convolutions with Hybrid Hadamard-based transform layers whose internal convolutions are implemented via multiplication-avoiding in-memory operations. We evaluate HTMA-Net on ResNet-18 using CIFAR-10, CIFAR-100, and Tiny ImageNet, and provide a detailed comparison against regular, MF-only, and HT-only variants. Results show that HTMA-Net eliminates up to 52\% of multiplications compared to baseline ResNet-18, ResNet-20, and ResNet-32 models, while achieving comparable accuracy in evaluation and significantly reducing computational complexity and the number of parameters. Our results demonstrate that combining structured Hadamard transform layers with SRAM-based in-memory computing multiplication-avoiding operators is a promising path towards efficient deep learning architectures.
format Preprint
id arxiv_https___arxiv_org_abs_2509_23103
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle HTMA-Net: Towards Multiplication-Avoiding Neural Networks via Hadamard Transform and In-Memory Computing
Hamdan, Emadeldeen
Cetin, Ahmet Enis
Computer Vision and Pattern Recognition
Artificial Intelligence
Reducing the cost of multiplications is critical for efficient deep neural network deployment, especially in energy-constrained edge devices. In this work, we introduce HTMA-Net, a novel framework that integrates the Hadamard Transform (HT) with multiplication-avoiding (MA) SRAM-based in-memory computing to reduce arithmetic complexity while maintaining accuracy. Unlike prior methods that only target multiplications in convolutional layers or focus solely on in-memory acceleration, HTMA-Net selectively replaces intermediate convolutions with Hybrid Hadamard-based transform layers whose internal convolutions are implemented via multiplication-avoiding in-memory operations. We evaluate HTMA-Net on ResNet-18 using CIFAR-10, CIFAR-100, and Tiny ImageNet, and provide a detailed comparison against regular, MF-only, and HT-only variants. Results show that HTMA-Net eliminates up to 52\% of multiplications compared to baseline ResNet-18, ResNet-20, and ResNet-32 models, while achieving comparable accuracy in evaluation and significantly reducing computational complexity and the number of parameters. Our results demonstrate that combining structured Hadamard transform layers with SRAM-based in-memory computing multiplication-avoiding operators is a promising path towards efficient deep learning architectures.
title HTMA-Net: Towards Multiplication-Avoiding Neural Networks via Hadamard Transform and In-Memory Computing
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2509.23103