# EuclidNets: An Alternative Operation for Efficient Inference of Deep Learning Models

arXiv: https://arxiv.org/abs/2212.11803 · HTML: https://mlsanity.com/paper/2212.11803/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 27 of its 57 references that are in the map.
- First posted on arXiv 22 Dec 2022.

## Builds on (most cited first, 27 of 27)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [Mask R-CNN](https://mlsanity.com/paper/1703.06870/) (2017)
- [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://mlsanity.com/paper/1905.11946/) (2019)
- [MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications](https://mlsanity.com/paper/1704.04861/) (2017)
- [The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks](https://mlsanity.com/paper/1803.03635/) (2018)
- [Rethinking Atrous Convolution for Semantic Image Segmentation](https://mlsanity.com/paper/1706.05587/) (2017)
- [ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices](https://mlsanity.com/paper/1707.01083/) (2017)
- [SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size](https://mlsanity.com/paper/1602.07360/) (2016)
- [A Survey of Model Compression and Acceleration for Deep Neural Networks](https://mlsanity.com/paper/1710.09282/) (2017)
- [Integer Quantization for Deep Learning Inference: Principles and Empirical Evaluation](https://mlsanity.com/paper/2004.09602/) (2020)
- [HashNet: Deep Learning to Hash by Continuation](https://mlsanity.com/paper/1702.00758/) (2017)
- [AdderNet: Do We Really Need Multiplications in Deep Learning?](https://mlsanity.com/paper/1912.13200/) (2019)
- [A Survey on Methods and Theories of Quantized Neural Networks](https://mlsanity.com/paper/1808.04752/) (2018)
- [A Comprehensive Survey on Hardware-Aware Neural Architecture Search](https://mlsanity.com/paper/2101.09336/) (2021)
- [ShiftAddNet: A Hardware-Inspired Deep Network](https://mlsanity.com/paper/2010.12785/) (2020)
- [Kernel Based Progressive Distillation for Adder Neural Networks](https://mlsanity.com/paper/2009.13044/) (2020)
- [Mollifying Networks](https://mlsanity.com/paper/1608.04980/) (2016)
- [Morphological Network: How Far Can We Go with Morphological Neurons?](https://mlsanity.com/paper/1901.00109/) (2019)
- [Training Recurrent Neural Networks by Diffusion](https://mlsanity.com/paper/1601.04114/) (2016)
- [A homotopy training algorithm for fully connected neural networks](https://mlsanity.com/paper/1903.09872/) (2019)
- [Activation Adaptation in Neural Networks](https://mlsanity.com/paper/1901.09849/) (2019)
- [ResNet-like Architecture with Low Hardware Requirements](https://mlsanity.com/paper/2009.07190/) (2020)
- [No Multiplication? No Floating Point? No Problem! Training Networks for Efficient Inference](https://mlsanity.com/paper/1809.09244/) (2018)
- [Table-Based Neural Units: Fully Quantizing Networks for Multiply-Free Inference](https://mlsanity.com/paper/1906.04798/) (2019)
- [Bipolar Morphological Neural Networks: Convolution Without Multiplication](https://mlsanity.com/paper/1911.01971/) (2019)

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

- [Metric as Transform: Exploring beyond Affine Transform for Interpretable Neural Network](https://mlsanity.com/paper/2410.16159/) (2024)

## Abstract (arXiv)

With the advent of deep learning application on edge devices, researchers actively try to optimize their deployments on low-power and restricted memory devices. There are established compression method such as quantization, pruning, and architecture search that leverage commodity hardware. Apart from conventional compression algorithms, one may redesign the operations of deep learning models that lead to more efficient implementation. To this end, we propose EuclidNet, a compression method, designed to be implemented on hardware which replaces multiplication, xw, with Euclidean distance (x-w)2. We show that EuclidNet is aligned with matrix multiplication and it can be used as a measure of similarity in case of convolutional layers. Furthermore, we show that under various transformations and noise scenarios, EuclidNet exhibits the same performance compared to the deep learning models designed with multiplication operations.