Theory of Computing: Goals and Directions (PDF, from 1996) Computer Science |
- Theory of Computing: Goals and Directions (PDF, from 1996)
- Beyond Log-Concave Sampling (a discussion of the sampling analogue to optimization's convexity)
- Blog on Articulation Points and Bridges in Graph Theory
- New tool for CS-ML students: Chrome/Firefox extension for finding CV/ML/AI Code Implementations!
- State of the art in Crop/Weed Segmentation!
- [R] Facebook AI Enables Automatic Closed Captions for Facebook Live
- [R] Human Feedback Improves OpenAI Model Summarizations
- Latest from NVIDIA: State of the art in capturing the shape and spatially-varying appearance!
- [blog] Mathematics and Computation | A general definition of dependent type theories
- "Intro to Higher Math" e-textbook by Whitman College
- Check out this Free ML tool: Browser extension for ML/AI Code Implementation Finder!
| Theory of Computing: Goals and Directions (PDF, from 1996) Posted: 20 Sep 2020 02:30 PM PDT |
| Beyond Log-Concave Sampling (a discussion of the sampling analogue to optimization's convexity) Posted: 20 Sep 2020 05:40 PM PDT |
| Blog on Articulation Points and Bridges in Graph Theory Posted: 20 Sep 2020 12:24 PM PDT |
| New tool for CS-ML students: Chrome/Firefox extension for finding CV/ML/AI Code Implementations! Posted: 16 Sep 2020 06:46 PM PDT |
| State of the art in Crop/Weed Segmentation! Posted: 16 Sep 2020 01:09 PM PDT |
| [R] Facebook AI Enables Automatic Closed Captions for Facebook Live Posted: 15 Sep 2020 01:49 PM PDT Facebook AI researchers and engineers just made live video content more accessible by enabling automatic closed captions for Facebook Live and Workplace Live, the company announced today. Here is a quick read: Facebook AI Enables Automatic Closed Captions for Facebook Live [link] [comments]  |
| [R] Human Feedback Improves OpenAI Model Summarizations Posted: 15 Sep 2020 11:12 AM PDT In a new paper, a team of OpenAI researchers sets out to advance methods for training large-scale language models such as BERT on objectives that more closely capture human preferences — and does so by putting humans back into the loop. The work focuses on abstractive English text summarization — a subjective task that's considered challenging because the notion of what makes a "good summary" is difficult to capture without human input. Here is a quick read: Human Feedback Improves OpenAI Model Summarizations The paper Learning to Summarize from Human Feedback is on arXiv. [link] [comments]  |
| Latest from NVIDIA: State of the art in capturing the shape and spatially-varying appearance! Posted: 15 Sep 2020 09:47 AM PDT |
| [blog] Mathematics and Computation | A general definition of dependent type theories Posted: 15 Sep 2020 12:50 AM PDT |
| "Intro to Higher Math" e-textbook by Whitman College Posted: 14 Sep 2020 10:39 AM PDT |
| Check out this Free ML tool: Browser extension for ML/AI Code Implementation Finder! Posted: 14 Sep 2020 02:30 PM PDT |
| You are subscribed to email updates from Computer Science: Theory and Application. To stop receiving these emails, you may unsubscribe now. | Email delivery powered by Google |
| Google, 1600 Amphitheatre Parkway, Mountain View, CA 94043, United States | |
No comments:
Post a Comment