Summary of The Impact Of Model Size on Catastrophic Forgetting in Online Continual Learning, by Eunhae Lee
The impact of model size on catastrophic forgetting in Online Continual Learning
by Eunhae Lee
First submitted to arxiv on: 28 Jun 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Computer Vision and Pattern Recognition (cs.CV)
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 research explores the connection between model size and Online Continual Learning performance, focusing on catastrophic forgetting. The study uses ResNet architectures of varying sizes and the SplitCIFAR-10 dataset to examine how network depth and width affect model performance in class-incremental learning. Key findings show that larger models do not always perform better; instead, they often struggle more in adapting to new tasks, especially in online settings. This challenges the idea that larger models inherently mitigate catastrophic forgetting, highlighting the complex relationship between model size and Continual Learning efficacy. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This study looks at how big a model is and how well it can learn new things without forgetting what it already knows. They used different-sized ResNet models and tested them on pictures of objects. What they found was that bigger models don’t always do better; sometimes, they even have trouble learning new things. This means we need to think more about why this happens and how we can make models that are good at both remembering old things and learning new ones. |
Keywords
* Artificial intelligence * Continual learning * Resnet
