你可能會喜歡
Since this seriously helped a friend the other day: If your network doesn't learn, reduce the dataset to a small batch (eg 32 examples) and try to overfit on it. The loss should be near zero (because the network should be able to memorize it); if not, there's a bug in your code.
What is your favorite ML tip or trick that has stood the test of time? #ML #AI #DeepLearning #Research
The fastai mooc is how I got started. I love the top-down, approach. It gets you started right out of the box. 90% of my first capstone was built on what I learned in just the first two classes. I'm deeply grateful to all the @fastdotai community. <3
After 2 years, Practical Deep Learning for Coders v5 is finally ready! 🎊 This is a from-scratch rewrite of our most popular course. It has a focus on interactive explorations, & covers @PyTorch, @huggingface, DeBERTa, ConvNeXt, @Gradio & other goodies 🧵 course.fast.ai
I've built a @Gradio demo on how @scikit_learn classifiers perform on the same dataset 🌌 ✨ See it in action here: huggingface.co/spaces/scikit-… 👀 Keep an eye on scikit-learn organization at @huggingface for more demos! huggingface.co/scikit-learn
Exploring Neural Networks Visually in the Browser - Casey Primozic's Homepage bit.ly/3vq7OAZ #AI #DeepLearning #MachineLearning #DataScience
nvt op Tuesday! 🤖 Remember those @kaggle kernels where a person goes meticulously though the hundreds of columns in a DataFrame to reduce their size? What if I told you there exists an automated way to do just that? 😎
Square One Bias in NLP: Towards a Multi-Dimensional Exploration of the Research Manifold (ACL 2022) We identify the current prototypical NLP experiment (the “square one”) and assess the dimensions along which NLP papers go beyond this prototype. aclanthology.org/2022.findings-…
20 questions to practice for machine learning interviews. These questions focus mostly on neural networks. They cover some fundamental concepts you should know. ↓
⚡️It's LIVE: **No ML Degree** My 60-page guide on how to land your first machine learning job without a degree. Amazon: amazon.com/dp/B0B1XFF1F8 Gumroad: emilwallner.gumroad.com/l/no-ml-degree 👉 The resources that *really* matter, building industry portfolios, and ideal job opportunities.
Simple animations can go a long way in making concepts easier to understand. This is my first attempt at it, and the video attempts to visualize the effect of ReLU while solving a classification problem. lnkd.in/gJhcGp7 #DeepLearning #AI
United States 趨勢
- 1. Steelers 67.6K posts
- 2. Tucker Kraft 11.5K posts
- 3. Packers 49.6K posts
- 4. Tomlin 7,280 posts
- 5. Jordan Love 8,308 posts
- 6. #GoPackGo 8,462 posts
- 7. Austin Reaves 8,574 posts
- 8. Rodgers 32.6K posts
- 9. #HereWeGo 6,888 posts
- 10. Nixon 13.6K posts
- 11. McManus 3,546 posts
- 12. Teryl Austin 1,381 posts
- 13. Brian Kelly 54.9K posts
- 14. Green Bay 9,229 posts
- 15. #WelcomeToDerry 2,196 posts
- 16. #RHOP 8,035 posts
- 17. Boswell 3,039 posts
- 18. Zeus 17.3K posts
- 19. #BaddiesAfricaReunion 4,323 posts
- 20. Josh Jacobs 1,834 posts
Something went wrong.
Something went wrong.