What question did this study set out to answer?

This work aims to evaluate lightweight deep learning architectures for effective use on edge devices.

May 2, 2026Open Access

Bridging Accuracy And Latency: An Edge- Centric Study Of Lightweight Deep Neural Architectures

View Full Paper

Ask AI

Bookmark

This work aims to evaluate lightweight deep learning architectures for effective use on edge devices.
Examined MobileNetV2, SqueezeNet, and EfficientNet-B0 for real-time inference on edge devices.
Utilized the CIFAR-10 dataset for performance benchmarking.
Implemented transfer learning, structured pruning, and dynamic quantization to optimize model efficiency.
EfficientNet-B0 achieved the highest classification accuracy of 92.06%.
SqueezeNet provided faster inference due to fewer parameters.
MobileNetV2 showed a balanced trade-off between accuracy and latency.

No takes yet. Share an insight, caveat, or question.

Randomized trial examines model performance in edge environments, highlighting accuracy and speed trade-offs.

Takkar et al. (2026) studied this question.

View Full Paper

Ask AI

Bookmark