# OscNet: Machine Learning on CMOS Oscillator Networks

arXiv: https://arxiv.org/abs/2502.07192 · HTML: https://mlsanity.com/paper/2502.07192/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 86 references that are in the map.
- First posted on arXiv 11 Feb 2025.

## Builds on (most cited first, 19 of 19)

- [Ising formulations of many NP problems](https://mlsanity.com/paper/1302.5843/) (2013)
- [Power Hungry Processing: Watts Driving the Cost of AI Deployment?](https://mlsanity.com/paper/2311.16863/) (2023)
- [SpatialBot: Precise Spatial Understanding with Vision Language Models](https://mlsanity.com/paper/2406.13642/) (2024)
- [Recent Advances in Autoencoder-Based Representation Learning](https://mlsanity.com/paper/1812.05069/) (2018)
- [Deep physical neural networks enabled by a backpropagation algorithm for arbitrary physical systems](https://mlsanity.com/paper/2104.13386/) (2021)
- [A Survey of Neuromorphic Computing and Neural Networks in Hardware](https://mlsanity.com/paper/1705.06963/) (2017)
- [Compute and Energy Consumption Trends in Deep Learning Inference](https://mlsanity.com/paper/2109.05472/) (2021)
- [Hebbian Deep Learning Without Feedback](https://mlsanity.com/paper/2209.11883/) (2022)
- [Unsupervised Learning by Competing Hidden Units](https://mlsanity.com/paper/1806.10181/) (2018)
- [VDD: Varied Drone Dataset for Semantic Segmentation](https://mlsanity.com/paper/2305.13608/) (2023)
- [SoftHebb: Bayesian Inference in Unsupervised Hebbian Soft Winner-Take-All Networks](https://mlsanity.com/paper/2107.05747/) (2021)
- [Self-learning Machines based on Hamiltonian Echo Backpropagation](https://mlsanity.com/paper/2103.04992/) (2021)
- [Hebbian learning with gradients: Hebbian convolutional neural networks with modern deep learning frameworks](https://mlsanity.com/paper/2107.01729/) (2021)
- [An Analysis of Unsupervised Pre-training in Light of Recent Advances](https://mlsanity.com/paper/1412.6597/) (2014)
- [Object-level Geometric Structure Preserving for Natural Image Stitching](https://mlsanity.com/paper/2402.12677/) (2024)
- [Effect of top-down connections in Hierarchical Sparse Coding](https://mlsanity.com/paper/2002.00892/) (2020)
- [Neural networks grown and self-organized by noise](https://mlsanity.com/paper/1906.01039/) (2019)
- [Training Convolutional Neural Networks With Hebbian Principal Component Analysis](https://mlsanity.com/paper/2012.12229/) (2020)
- [Probabilistic Modeling of Disparity Uncertainty for Robust and Efficient Stereo Matching](https://mlsanity.com/paper/2412.18703/) (2024)

## Built on by (most cited first, 2 of 2)

- [RoboFAC: A Comprehensive Framework for Robotic Failure Analysis and Correction](https://mlsanity.com/paper/2505.12224/) (2025)
- [OscNet v1.5: Energy Efficient Hopfield Network on CMOS Oscillators for Image Classification](https://mlsanity.com/paper/2506.12610/) (2025)

## Abstract (arXiv)

Machine learning and AI have achieved remarkable advancements but at the cost of significant computational resources and energy consumption. This has created an urgent need for a novel, energy-efficient computational fabric to replace the current computing pipeline. Recently, a promising approach has emerged by mimicking spiking neurons in the brain and leveraging oscillators on CMOS for direct computation. In this context, we propose a new and energy efficient machine learning framework implemented on CMOS Oscillator Networks (OscNet). We model the developmental processes of the prenatal brain's visual system using OscNet, updating weights based on the biologically inspired Hebbian rule. This same pipeline is then directly applied to standard machine learning tasks. OscNet is a specially designed hardware and is inherently energy-efficient. Its reliance on forward propagation alone for training further enhances its energy efficiency while maintaining biological plausibility. Simulation validates our designs of OscNet architectures. Experimental results demonstrate that Hebbian learning pipeline on OscNet achieves performance comparable to or even surpassing traditional machine learning algorithms, highlighting its potential as a energy efficient and effective computational paradigm.