# OscNet v1.5: Energy Efficient Hopfield Network on CMOS Oscillators for Image Classification

arXiv: https://arxiv.org/abs/2506.12610 · HTML: https://mlsanity.com/paper/2506.12610/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 7 of its 27 references that are in the map.
- First posted on arXiv 14 Jun 2025.

## Builds on (most cited first, 7 of 7)

- [Hopfield Networks is All You Need](https://mlsanity.com/paper/2008.02217/) (2020)
- [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)
- [Compute and Energy Consumption Trends in Deep Learning Inference](https://mlsanity.com/paper/2109.05472/) (2021)
- [Hardware Acceleration of Sparse and Irregular Tensor Computations of ML Models: A Survey and Insights](https://mlsanity.com/paper/2007.00864/) (2020)
- [OscNet: Machine Learning on CMOS Oscillator Networks](https://mlsanity.com/paper/2502.07192/) (2025)
- [Shem: A Hardware-Aware Optimization Framework for Analog Computing Systems](https://mlsanity.com/paper/2411.03557/) (2024)

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

- [Generative Models on Analog Hardware with Dynamics](https://mlsanity.com/paper/2606.27294/) (2026)

## Abstract (arXiv)

Machine learning has achieved remarkable advancements but at the cost of significant computational resources. This has created an urgent need for a novel and energy-efficient computational fabric and corresponding algorithms. CMOS Oscillator Networks (OscNet) is a brain inspired and specially designed hardware for low energy consumption. In this paper, we propose a Hopfield Network based machine learning algorithm that can be implemented on OscNet. The network is trained using forward propagation alone to learn sparsely connected weights, yet achieves an 8% improvement in accuracy compared to conventional deep learning models on MNIST dataset. OscNet v1.5 achieves competitive accuracy on MNIST and is well-suited for implementation using CMOS-compatible ring oscillator arrays with SHIL. In oscillator-based inference, we utilize only 24% of the connections used in a fully connected Hopfield network, with merely a 0.1% drop in accuracy. OscNet v1.5 relies solely on forward propagation and employs sparse connections, making it an energy-efficient machine learning pipeline designed for oscillator computing fabric. The repository for OscNet family is: https://github.com/RussRobin/OscNet .