BROWSE
Detail
Journal Article
Automated deep‐learning model optimization framework for microcontrollers
- Authors
- Seungtae Hong, Gunju Park, Jeong‐Si Kim
- Issue Date
- 2025-04
- Citation
- ETRI Journal, v.47, no.2, pp.179-192
- ISSN
- 1225-6463
- Publisher
- 한국전자통신연구원
- Language
- English
- Type
- Journal Article
- Abstract
- This paper introduces a framework for optimizing deep‐learning models on microcontrollers (MCUs) that is crucial in today's expanding embedded device market. We focus on model optimization techniques, particularly pruning and quantization, to enhance the performance of neural networks within the limited resources of MCUs. Our approach combines automatic iterative optimization and code generation, simplifying MCU model deployment without requiring extensive hardware knowledge. Based on experiments with architectures, such as ResNet‐8 and MobileNet v2, our framework substantially reduces the model size and enhances inference speed that are crucial for MCU efficiency. Compared with TensorFlow Lite for MCUs, our optimizations for MobileNet v2 reduce static random‐access memory use by 51%–57% and flash use by 17%–62%, while increasing inference speed by approximately 1.55 times. These advancements highlight the impact of our method on performance and memory efficiency, demonstrating its value in embedded artificial intelligence and broad applicability in MCU‐based neural network optimization.
- KSP Keywords
- Embedded artificial intelligence, Embedded devices, Iterative Optimization, Limited resources, Memory Efficiency, Model deployment, Model optimization, Neural network optimization, Optimization framework, Optimization techniques, code generation
This work is distributed under the term of Korea Open Government License (KOGL)
(Type 4: : Type 1 + Commercial Use Prohibition+Change Prohibition)
(Type 4: : Type 1 + Commercial Use Prohibition+Change Prohibition)
