# Big-Little Adaptive Neural Networks on Low-Power Near-Subthreshold Processors

arXiv: https://arxiv.org/abs/2304.09695 · HTML: https://mlsanity.com/paper/2304.09695/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 41 references that are in the map.
- First posted on arXiv 19 Apr 2023.

## Builds on (most cited first, 9 of 9)

- [Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference](https://mlsanity.com/paper/1712.05877/) (2017)
- [XNOR-Net: ImageNet Classification Using Binary Convolutional Neural Networks](https://mlsanity.com/paper/1603.05279/) (2016)
- [BranchyNet: Fast Inference via Early Exiting from Deep Neural Networks](https://mlsanity.com/paper/1709.01686/) (2017)
- [Quantized Neural Networks: Training Neural Networks with Low Precision Weights and Activations](https://mlsanity.com/paper/1609.07061/) (2016)
- [Edge Intelligence: Paving the Last Mile of Artificial Intelligence with Edge Computing](https://mlsanity.com/paper/1905.10083/) (2019)
- [Binarized Neural Networks: Training Deep Neural Networks with Weights and Activations Constrained to +1 or -1](https://mlsanity.com/paper/1602.02830/) (2016)
- [Quantization and Deployment of Deep Neural Networks on Microcontrollers](https://mlsanity.com/paper/2105.13331/) (2021)
- [FANN-on-MCU: An Open-Source Toolkit for Energy-Efficient Neural Network Inference at the Edge of the Internet of Things](https://mlsanity.com/paper/1911.03314/) (2019)
- [CoopNet: Cooperative Convolutional Neural Network for Low-Power MCUs](https://mlsanity.com/paper/1911.08606/) (2019)

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

- [Edge Deep Learning in Computer Vision and Medical Diagnostics: A Comprehensive Survey](https://mlsanity.com/paper/2605.06714/) (2026)
- [Edge AI for Internet of Energy: Challenges and Perspectives](https://mlsanity.com/paper/2311.16851/) (2023)

## Abstract (arXiv)

This paper investigates the energy savings that near-subthreshold processors can obtain in edge AI applications and proposes strategies to improve them while maintaining the accuracy of the application. The selected processors deploy adaptive voltage scaling techniques in which the frequency and voltage levels of the processor core are determined at the run-time. In these systems, embedded RAM and flash memory size is typically limited to less than 1 megabyte to save power. This limited memory imposes restrictions on the complexity of the neural networks model that can be mapped to these devices and the required trade-offs between accuracy and battery life. To address these issues, we propose and evaluate alternative 'big-little' neural network strategies to improve battery life while maintaining prediction accuracy. The strategies are applied to a human activity recognition application selected as a demonstrator that shows that compared to the original network, the best configurations obtain an energy reduction measured at 80% while maintaining the original level of inference accuracy.