Summary of Tenns-pleiades: Building Temporal Kernels with Orthogonal Polynomials, by Yan Ru Pei et al.
TENNs-PLEIADES: Building Temporal Kernels with Orthogonal Polynomials
by Yan Ru Pei, Olivier Coenen
First submitted to arxiv on: 20 May 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 The PLEIADES neural network, a type of Temporal Neural Network (TENN), is designed to perform online spatiotemporal classification and detection using event-based data. This architecture allows for the variation of sample rates and discretization step-sizes without additional finetuning. The authors achieved state-of-the-art results on three benchmarks, including hand gesture recognition, eye tracking, and automotive detection, with significantly reduced memory and compute costs. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary The PLEIADES neural network is a new way to do computer vision using special kinds of data called event-based data. This means the data comes in small pieces that can be processed quickly. The researchers made this network work really well on three different tasks: recognizing hand gestures, tracking eyes, and detecting cars. They were able to get better results than others who did similar tasks, but used more memory and computer power. |
Keywords
» Artificial intelligence » Classification » Gesture recognition » Neural network » Spatiotemporal » Tracking
