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

arXiv: https://arxiv.org/abs/2509.23103 · HTML: https://mlsanity.com/paper/2509.23103/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 13 of its 23 references that are in the map.
- First posted on arXiv 27 Sep 2025.

## Builds on (most cited first, 13 of 13)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications](https://mlsanity.com/paper/1704.04861/) (2017)
- [XNOR-Net: ImageNet Classification Using Binary Convolutional Neural Networks](https://mlsanity.com/paper/1603.05279/) (2016)
- [Deep Scattering Spectrum](https://mlsanity.com/paper/1304.6763/) (2013)
- [A comprehensive review of Binary Neural Network](https://mlsanity.com/paper/2110.06804/) (2021)
- [Fast Walsh-Hadamard Transform and Smooth-Thresholding Based Binary Layers in Deep Neural Networks](https://mlsanity.com/paper/2104.07085/) (2021)
- [Block Walsh-Hadamard Transform Based Binary Layers in Deep Neural Networks](https://mlsanity.com/paper/2201.02711/) (2022)
- [Energy Efficient Hadamard Neural Networks](https://mlsanity.com/paper/1805.05421/) (2018)
- [MF-Net: Compute-In-Memory SRAM for Multibit Precision Inference using Memory-immersed Data Conversion and Multiplication-free Operators](https://mlsanity.com/paper/2102.00035/) (2021)
- [A Hybrid Quantum-Classical Approach based on the Hadamard Transform for the Convolutional Layer](https://mlsanity.com/paper/2305.17510/) (2023)
- [Combating the Memory Walls: Optimization Pathways for Long-Context Agentic LLM Inference](https://mlsanity.com/paper/2509.09505/) (2025)
- [A Probabilistic Hadamard U-Net for MRI Bias Field Correction](https://mlsanity.com/paper/2403.05024/) (2024)

## Built on by (most cited first, 1 of 1)

- [Learned Queries and Keys Are All You Need: Replacing the Value Projection with Structured Transforms](https://mlsanity.com/paper/2609.36698/) (2026)

## Abstract (arXiv)

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.