# EVE: Environmental Adaptive Neural Network Models for Low-power Energy Harvesting System

arXiv: https://arxiv.org/abs/2207.09258 · HTML: https://mlsanity.com/paper/2207.09258/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 32 references that are in the map.
- First posted on arXiv 14 Jul 2022.

## Builds on (most cited first, 15 of 15)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Neural Architecture Search with Reinforcement Learning](https://mlsanity.com/paper/1611.01578/) (2016)
- [Speech Commands: A Dataset for Limited-Vocabulary Speech Recognition](https://mlsanity.com/paper/1804.03209/) (2018)
- [Edge AI: On-Demand Accelerating Deep Neural Network Inference via Edge Computing](https://mlsanity.com/paper/1910.05316/) (2019)
- [PatDNN: Achieving Real-Time DNN Execution on Mobile Devices with Pattern-based Weight Pruning](https://mlsanity.com/paper/2001.00138/) (2020)
- [SqueezeNext: Hardware-Aware Neural Network Design](https://mlsanity.com/paper/1803.10615/) (2018)
- [PCONV: The Missing but Desirable Sparsity in DNN Weight Pruning for Real-time Execution on Mobile Devices](https://mlsanity.com/paper/1909.05073/) (2019)
- [Co-Exploration of Neural Architectures and Heterogeneous ASIC Accelerator Designs Targeting Multiple Tasks](https://mlsanity.com/paper/2002.04116/) (2020)
- [Accelerating Framework of Transformer by Hardware Design and Model Compression Co-Optimization](https://mlsanity.com/paper/2110.10030/) (2021)
- [Intelligence Beyond the Edge: Inference on Intermittent Embedded Systems](https://mlsanity.com/paper/1810.07751/) (2018)
- [Binary Complex Neural Network Acceleration on FPGA](https://mlsanity.com/paper/2108.04811/) (2021)
- [Dancing along Battery: Enabling Transformer with Run-time Reconfigurability on Mobile Devices](https://mlsanity.com/paper/2102.06336/) (2021)
- [Enabling Fast Deep Learning on Tiny Energy-Harvesting IoT Devices](https://mlsanity.com/paper/2111.14051/) (2021)
- [SMOF: Squeezing More Out of Filters Yields Hardware-Friendly CNN Pruning](https://mlsanity.com/paper/2110.10842/) (2021)

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

- [AdaPI: Facilitating DNN Model Adaptivity for Efficient Private Inference in Edge Computing](https://mlsanity.com/paper/2407.05633/) (2024)
- [Physics-aware Roughness Optimization for Diffractive Optical Neural Networks](https://mlsanity.com/paper/2304.01500/) (2023)

## Abstract (arXiv)

IoT devices are increasingly being implemented with neural network models to enable smart applications. Energy harvesting (EH) technology that harvests energy from ambient environment is a promising alternative to batteries for powering those devices due to the low maintenance cost and wide availability of the energy sources. However, the power provided by the energy harvester is low and has an intrinsic drawback of instability since it varies with the ambient environment. This paper proposes EVE, an automated machine learning (autoML) co-exploration framework to search for desired multi-models with shared weights for energy harvesting IoT devices. Those shared models incur significantly reduced memory footprint with different levels of model sparsity, latency, and accuracy to adapt to the environmental changes. An efficient on-device implementation architecture is further developed to efficiently execute each model on device. A run-time model extraction algorithm is proposed that retrieves individual model with negligible overhead when a specific model mode is triggered.Experimental results show that the neural networks models generated by EVE is on average 2.5X times faster than the baseline models without pruning and shared weights.