Summary of Realtime Facial Expression Recognition: Neuromorphic Hardware Vs. Edge Ai Accelerators, by Heath Smith et al.
Realtime Facial Expression Recognition: Neuromorphic Hardware vs. Edge AI Accelerators
by Heath Smith, James Seekings, Mohammadreza Mohammadi, Ramtin Zand
First submitted to arxiv on: 30 Jan 2024
Categories
- Main: Computer Vision and Pattern Recognition (cs.CV)
- Secondary: Machine Learning (cs.LG); Neural and Evolutionary Computing (cs.NE); Performance (cs.PF)
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 investigates two hardware options for deploying facial expression recognition (FER) machine learning models at the edge: neuromorphic hardware and edge AI accelerators. The authors compare the Intel Loihi neuromorphic processor with four distinct edge platforms, including Raspberry Pi-4, Intel Neural Compute Stick (NSC), Jetson Nano, and Coral TPU. The results show that Loihi achieves approximately two orders of magnitude reduction in power dissipation and one order of magnitude energy savings compared to Coral TPU, while maintaining comparable accuracy within real-time latency requirements. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary In this study, researchers explored ways to deploy facial expression recognition models on edge devices, like robots. They tested different hardware options, including a special chip called Loihi, and four other types of edge devices. The results showed that Loihi uses much less power and energy than the others, while still being very accurate. This is important for real-world applications where speed and efficiency matter. |
Keywords
* Artificial intelligence * Machine learning
