Summary of On the Hardness Of Training Deep Neural Networks Discretely, by Ilan Doron-arad
On the Hardness of Training Deep Neural Networks Discretely
by Ilan Doron-Arad
First submitted to arxiv on: 17 Dec 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 explores neural network training optimization for deep networks, building on existing research on two-layer networks. It focuses on the challenges of optimizing neural networks with more than two layers, which have been shown to perform better in practice. The study also delves into the discrete variant of neural network training, where parameters are chosen from a finite set of options. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary The paper looks at how to make neural networks work better by adjusting their “weights” and “biases”. It focuses on bigger networks with more layers, which do a better job in real-life tasks. The study also investigates the opposite problem: when can we only choose from a small set of options for these weights and biases? |
Keywords
» Artificial intelligence » Neural network » Optimization
