AI & machine learning2015 · shared on Hacker News
Distilling the Knowledge in a Neural Network
Explore Distilling the Knowledge in a Neural Network, its original source and Hacker News discussions. Discover community perspectives and save it to your reading list.
GO BEYOND THE ABSTRACT
The conversation around the idea.
Original Hacker News threads. Different perspectives, questions, and things worth thinking about.
Showing up to 100 related threads. A paper may appear in a comment rather than the original submission.
Links found in the discussion
Up to 50 recent source links, in HN item order.
Comment #49013128 Comment #47449671 Comment #44668990 Comment #40935003 Comment #38559362 Comment #35392221 Comment #35153639 Comment #30890862 Comment #25131520 Comment #16339544 Comment #15859663 Comment #14985722 Comment #14209003 Comment #13564478 Comment #13172889 Comment #11274120 Comment #9969737 Comment #9969442
YFede_V ·
AlphaGo beats Lee Sedol 3-0 [video]
566 points407 comments
Yxwintermutex ·
How Google Translate squeezes deep learning onto a phone
403 points92 comments
Yrwieruch ·
Neural Networks in JavaScript with Deeplearn.js
396 points72 comments
Ymortenjorck ·
The Myth of a Superhuman AI
254 points357 comments
Ysarthakjain ·
How to use Deep Learning when you have Limited Data
252 points50 comments
Ygroar ·
Neurogenesis Deep Learning
197 points97 comments
Ypseudolus ·
Distillation makes AI models smaller and cheaper
164 points82 comments
YAnon84 ·
Training of Physical Neural Networks
142 points46 comments
Ypete_b_condon ·
New Explainable AI Algorithms
111 points18 comments
Yjpindar ·
Inside Darpa’s Push to Make Artificial Intelligence Explain Itself
88 points47 comments
Yzeveb ·
The crisis of American forensics
74 points15 comments
Yprostoalex ·
Scientists discover specific neurons involved in making memories
56 points9 comments
Ysirteno ·
Could you train a ChatGPT-beating model for $85,000 and run it in a browser?
8 points0 comments
YPaulHoule ·
Efficient Transformer Knowledge Distillation: A Performance Review
7 points0 comments
Ytim_sw ·
Distilling the Knowledge in a Neural Network
2 points0 comments
Ynabla9 ·
Eliezer Yudkowsky on large language model economics
2 points3 comments
Ysdpmas ·
NanoGPT Slowrun: 10x Data Efficiency with Infinite Compute
2 points0 comments
Ysoftwaredoug ·
"We have information that Moonshot distilled Fable for the development of K3"
2 points1 comments