Summary of Scan-edge: Finding Mobilenet-speed Hybrid Networks For Diverse Edge Devices Via Hardware-aware Evolutionary Search, by Hung-yueh Chiang et al.
SCAN-Edge: Finding MobileNet-speed Hybrid Networks for Diverse Edge Devices via Hardware-Aware Evolutionary Search
by Hung-Yueh Chiang, Diana Marculescu
First submitted to arxiv on: 27 Aug 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Artificial Intelligence (cs.AI)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary This paper proposes SCAN-Edge, a unified Neural Architecture Search (NAS) framework designed to optimize architectures for low-cost commodity edge devices. The authors aim to address the challenges of hardware-aware NAS by jointly searching for self-attention, convolution, and activation layers that accommodate diverse edge device hardware designs. A hardware-aware evolutionary algorithm is employed to accelerate the search process. The proposed approach is evaluated on large-scale datasets, demonstrating hybrid networks that match actual MobileNetV2 latency on various commodity devices. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper helps create better computer systems for smart devices like smartphones and cameras. It’s hard to design these systems because they need to work well with many different types of hardware. The researchers created a new way to find the best designs using a technique called Neural Architecture Search. This approach can be used on many different kinds of edge devices, which is important because each device has its own strengths and limitations. |
Keywords
» Artificial intelligence » Self attention
