Model Optimization Techniques for Embedded Artificial Intelligence

View Full Paper

Ask AI

Bookmark

Authors

Discussion

Analysis compares model optimization techniques for deep neural networks in resource-constrained systems, highlighting performance and efficiency.

Model optimization techniques enhance deep neural network performance while maintaining efficiency in embedded systems.
Key findings reveal accuracy retention through pruning, quantization, and dynamic inference—critical for limited resources.
Assessment involved experiments on architectures including ResNet, VGG, Inception, and MobileNet to explore efficiency trade-offs.
Future directions emphasize ongoing improvements in resource-constrained environments for deep learning applications.

Tianrui Hou (2025) studied this question.

View Full Paper

Ask AI

Bookmark

View Full Paper

Ask AI

Bookmark

Authors

Analysis compares model optimization techniques for deep neural networks in resource-constrained systems, highlighting performance and efficiency.

Model optimization techniques enhance deep neural network performance while maintaining efficiency in embedded systems.
Key findings reveal accuracy retention through pruning, quantization, and dynamic inference—critical for limited resources.
Assessment involved experiments on architectures including ResNet, VGG, Inception, and MobileNet to explore efficiency trade-offs.
Future directions emphasize ongoing improvements in resource-constrained environments for deep learning applications.

Tianrui Hou (2025) studied this question.

View Full Paper

Ask AI

Bookmark