Summary of Look Into the Lite in Deep Learning For Time Series Classification, by Ali Ismail-fawaz and Maxime Devanne and Stefano Berretti and Jonathan Weber and Germain Forestier
Look Into the LITE in Deep Learning for Time Series Classification
by Ali Ismail-Fawaz, Maxime Devanne, Stefano Berretti, Jonathan Weber, Germain Forestier
First submitted to arxiv on: 4 Sep 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: None
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 paper proposes a new architecture for Time Series Classification (TSC) called Light Inception with boosTing tEchnique (LITE), which reduces the number of trainable parameters while maintaining performance. The LITE architecture uses DepthWise Separable Convolutions (DWSC) and is boosted by three techniques: multiplexing, custom filters, and dilated convolution. Compared to state-of-the-art InceptionTime model, LITE is 2.78 times faster and consumes 2.79 times less CO2 and power. The paper also adapts the LITE architecture for multivariate time series data and evaluates its performance on a dataset representing human rehabilitation movements. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary The paper creates a new way to do Time Series Classification that uses fewer calculations than other top models, but still gets good results. It’s called Light Inception with boosTing tEchnique (LITE). LITE is faster and more environmentally friendly because it uses special types of neural network layers and techniques to help it learn. The paper also shows how this new model works on data that has multiple time series, like movements from people doing exercises. |
Keywords
» Artificial intelligence » Boosting » Classification » Neural network » Time series
