In this digital age, where deep learning is a hot topic, finding the right resources can feel like searching for a needle in a haystack. Enter Awesome AutoDL, a curated list of automated deep learning resources that aims to make your exploration much easier!
Table of Contents
- Awesome Blogs
- Awesome AutoDL Libraries
- Awesome Benchmarks
- Deep Learning-based NAS and HPO
- Awesome Surveys
Awesome Blogs
- AutoML info
- AutoML Freiburg-Hannover
- What’s the deal with Neural Architecture Search?
- Google Could AutoML
- PocketFlow
- AutoML Challenge
- AutoDL Challenge
- In Defense of Weight-sharing for Neural Architecture Search: an optimization perspective
Awesome AutoDL Libraries
Awesome Benchmarks
In a world bustling with benchmarks, it helps to have a well-structured list:
| Title | Venue | Code |
|---|---|---|
| NAS-Bench-101: Towards Reproducible Neural Architecture Search | ICML 2019 | GitHub |
| NAS-Bench-201 | ICLR 2020 | GitHub |
| NAS-Bench-301 and the Case for Surrogate Benchmarks | arXiv 2020 | GitHub |
| NAS-Bench-1Shot1 | ICLR 2020 | GitHub |
Deep Learning-based NAS and HPO
When diving into Neural Architecture Search (NAS), think of it as a treasure hunt:
You have a map (your data), and this map leads you to different lanes that represent various architecture types and methods, such as:
- Gradient-based
- Reinforcement Learning
- Evolutionary Algorithm
- Performance Prediction
- Other types
2021 Venues
A few notable entries from 2021 include:
- CATE: Computation-aware Neural Architecture Encoding with Transformers – ICML
- Searching by Generating – CVPR
Awesome Surveys
Surveys are like the overarching compass in the world of AutoML. Some notable ones include:
- A Comprehensive Survey of Neural Architecture Search: Challenges and Solutions – ACM Computing Surveys
- Automated Machine Learning on Graphs: A Survey – ICLR-W
Troubleshooting
If you encounter challenges while exploring these resources, consider the following:
- Ensure you have the latest version of any libraries or packages you’re using.
- Read through the documentation carefully; some nuances may require deeper understanding.
- Engage with the community through forums and contribute to the discussion.
- For bugs or issues, consider opening an issue or pull request on GitHub to seek assistance.
For more insights, updates, or to collaborate on AI development projects, stay connected with fxis.ai.
At fxis.ai, we believe that such advancements are crucial for the future of AI, as they enable more comprehensive and effective solutions. Our team is continually exploring new methodologies to push the envelope in artificial intelligence, ensuring that our clients benefit from the latest technological innovations.