HTMA-Net: Towards Multiplication-Avoiding Neural Networks via Hadamard Transform and In-Memory Computing
This work addresses efficiency challenges for deploying neural networks on edge devices, though it appears incremental as it builds on prior methods targeting multiplications and in-memory computing.
The paper tackles the problem of reducing multiplication costs in deep neural networks for energy-constrained edge devices by introducing HTMA-Net, which integrates Hadamard Transform with multiplication-avoiding in-memory computing, eliminating up to 52% of multiplications while maintaining comparable accuracy on datasets like CIFAR-10, CIFAR-100, and Tiny ImageNet.
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-50 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.