ATM-Net: Adaptive Termination and Multi-Precision Neural Networks for Energy-Harvested Edge Intelligence
Not on the map. Why?
Abstract (arXiv)
ATM-Net is a novel neural network architecture tailored for energy-harvested IoT devices, integrating adaptive termination points with multi-precision computing. It dynamically adjusts computational precision (32/8/4-bit) and network depth based on energy availability via early exit points. An energy-aware task scheduler optimizes the energy-accuracy trade-off. Experiments on CIFAR-10, PlantVillage, and TissueMNIST show ATM-Net achieves up to 96.93% accuracy while reducing power consumption by 87.5% with Q4 quantization compared to 32-bit operations. The power-delay product improves from 13.6J to 0.141J for DenseNet-121 and from 10.3J to 0.106J for ResNet-18, demonstrating its suitability for energy-harvesting systems.
Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). First posted on arXiv 13 Feb 2025.
Builds on
0 of 0 references.
No references here yet.
Built on by
Citing papers per year: 2026: 3.
3 papers.
Similar, not cited
Close in wording, no citation either way
- 2023Sustainable Edge Intelligence Through Energy-Aware Early Exiting
- 2024Energy-Aware Dynamic Neural Inference
- 2025Hardware-Algorithm Co-Optimization of Early-Exit Neural Networks for Multi-Core Edge Accelerators
- 2024Efficient Post-Training Augmentation for Adaptive Inference in Heterogeneous and Distributed IoT Environments
- 2023Early Exiting Predictive Coding Neural Networks for Edge AI
- 2024Memory-efficient Energy-adaptive Inference of Pre-Trained Models on Batteryless Embedded Systems
- 2022HADAS: Hardware-Aware Dynamic Neural Architecture Search for Edge Performance Scaling
- 2026SPARQ: Spiking Early-Exit Neural Networks for Energy-Efficient Edge AI