Summary of Machine Learning Vs Deep Learning: the Generalization Problem, by Yong Yi Bay and Kathleen A. Yearick
Machine Learning vs Deep Learning: The Generalization Problem
by Yong Yi Bay, Kathleen A. Yearick
First submitted to arxiv on: 3 Mar 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 study compares traditional machine learning (ML) models and deep learning (DL) algorithms in terms of extrapolation, which is crucial for real-world applications. The authors train both types of models on an exponentially growing function and test their performance on values outside the training domain. The results show that DL models can generalize beyond the training scope, while ML models struggle with this task. This paper highlights the importance of understanding the structural differences between ML and DL models, which has implications for both theoretical research and practical deployment. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This study looks at how well machine learning (ML) and deep learning (DL) models can predict things they haven’t seen before. The researchers trained both types of models on a special function that gets bigger and bigger, then tested them on values outside what they learned from. They found that DL models are good at making predictions about new data, while ML models have trouble doing this. This is important because in the real world, we often don’t have all the information, so our models need to be able to make smart guesses. |
Keywords
* Artificial intelligence * Deep learning * Machine learning
