upcarta
Sign In
Sign Up
Explore
Search
Deep learning
Follow
37
Followers
Most Recommended
Recent Content
Most Recommended
Paper
Book
Tweet
Video
Course
Article
Website
Podcast episode
Tweet
Apr 11, 2023
Artificial Neuron is the most fundamental unit of a Deep Neural Network. A conceptual thread🧵 twitter.com/arya_akhare/status/1645792224242982915/photo/1
by
Arya AI Dojo 👩🏻💻🤖
Post
Add to Collection
Mark as Completed
Tweet
Feb 27, 2023
🔭 A 🧵 on @OpenAI LLM "Alignment" (e.g. #ChatGPT) Q: How does this differ from publicly available "Instruction Tuning" (IT)? A: Proprietary Alignment is actually 3 separate components: 1⃣ Instruction tuning 2⃣ ➕ Open-ended generation/creative prompts
by
Shayne Longpre
Post
Add to Collection
Mark as Completed
Tweet
Feb 3, 2023
Our paper "Sample-Efficient Reinforcement Learning by Breaking the Replay Ratio Barrier" has been accepted to ICLR as top 5%! We show that lots of updates and resets lead to great sample efficiency. Come for the scaling, stay for the insights. o
by
Pierluca D'Oro
Post
Add to Collection
Mark as Completed
Tweet
Jan 5, 2023
Here's how I would study deep learning if I had to do it all over again. #deeplearning #machinelearning 👇🏽 🧵
by
Harpreet Sahota 🥑
Post
Add to Collection
Mark as Completed
Tweet
Mar 20, 2021
Deep learning excels at unlocking the creation of impressive early demos of new applications using very little development resources. The part where it struggles is reaching the level of consistent usefulness and reliability required by production u
by
François Chollet
Post
Add to Collection
Mark as Completed
Tweet
Apr 8, 2022
Latest preprint with Léon Bottou and @ylecun on the impact of regularization/data-augmentation on per-class performances (for better or worse)! Using them improves average generalization but some classes will have worse performance than without them
by
Randall Balestriero
Post
Add to Collection
Mark as Completed