Top all-time · #3908
Colin Raffel
Personal blog · colinraffel.com/blogaiscience
Colin Raffel's personal blog at colinraffel.com covers ai and science. Since 2016, 20 different Hacker News readers have linked it 21 times, most often “You Don't Know Jax”. No feed was found, so read it on the site itself.
Too few sampled comments (6) to say how often HN recommends it.?
Why HN links it
HN readers link Colin Raffel's site for a JAX basics tutorial, a wiki of deep learning paper summaries, and dataset pages such as the Lakh MIDI Dataset.
Summarised by Claude from a sample of 6 HN comments that link here. Each comment is marked recommending, critical or neutral (citing without judging); how this works.
Most-linked posts?
- You Don't Know Jax5 people · 5 mentions · first linked 2019-01-16
- A Call to Build Models Like We Build Open-Source Software5 people · 5 mentions · first linked 2021-12-08
- My Year at Brain2 people · 2 mentions · first linked 2017-08-24
- The Lakh MIDI Dataset v0.12 people · 2 mentions · first linked 2019-10-17
What Hacker News says?
Didn't say anything about algorithms improving faster than hardware. With better initialization and regularization, more efficient layers discovered by AutoML, sparsity, lower precision, or by directly combining models trained separately on diverse tasks instead of training sequentially we could have better models at the same hardware cost. Even by improving the way people collaborate on model training we could make…
Comment linking /blog/a-call-to-build-models-like-we-build-open-source-software.html
on “Moore's Law, AI, and the pace of progress”Submitted A Call to Build Models Like We Build Open-Source Software as a story · 71 points
HN discussionThank you! I found a great list of deep learning paper summaries that is mostly about learning algorithms from data and other cutting edge models: http://colinraffel.com/wiki/tag:neural_networks?do=showtag&t... all kudos to the owner/author of this list ! >NNs that manipulate existing code? e.g. parse it, find design pattern, optimize Also: you probably shouldn't need special architectures for such problems, these c…
Comment linking /wiki/tag:neural_networks?do=showtag&tag=Neural_Networks
on “How AI based programming could work”Submitted Build models like we build open-source software as a story · 51 points
HN discussionThe author proposes a lot of vague ideas in this article (for example "I believe one of the biggest problems is the use of Error Propagation and Gradient Descent") without references or any solid proofs why they are necessary to solve the proposed program (Automate programming using ML?). In fact there is already a lot of solid work just on this subject: * Learning algorithms from examples http://arxiv.org/abs/1511.…
Comment linking /wiki/a_roadmap_towards_machine_intelligence
on “How AI based programming could work”Submitted My Year at Brain as a story · 4 points
HN discussionNES APU sound synthesis chip is an ideal constraint for cross-domain learning with Transformers ;) LakhNES: Improving multi-instrumental music generation with cross-domain pre-training https://chrisdonahue.com/LakhNES/ The NES Music Database (5k+ scores) https://github.com/chrisdonahue/nesmdb The Lakh MIDI Dataset v0.1 (175k+ files) https://colinraffel.com/projects/lmd/
Comment linking /projects/lmd/
on “Ask HN: A good project for getting into Language Modelling?”Submitted You Don't Know Jax as a story · 3 points
HN discussionFYI MetaMIDI Dataset is the best (I found). you can request access here https://zenodo.org/record/5142664 if you haven’t already. Lakh MIDI Dataset https://colinraffel.com/projects/lmd is smaller but directly downloadable
Comment linking /projects/lmd
on “Ask HN: Is there a OS tool which queries MIDI datasets by chord progression/key?”Submitted You Don't Know JAX as a story · 3 points
HN discussionGreat basics tutorial: https://colinraffel.com/blog/you-don-t-know-jax.html
Comment linking /blog/you-don-t-know-jax.html
on “JAX – NumPy on the CPU, GPU, and TPU, with great automatic differentiation”Submitted You don't know Jax as a story · 3 points
HN discussionSubmitted Writing a Google AI Residency Cover Letter as a story · 3 points
HN discussionSubmitted GANs and Divergence Minimization as a story · 3 points
HN discussionSubmitted When will language models be good enough? as a story · 2 points
HN discussionSubmitted You Don't Know Jax as a story · 2 points
HN discussionSubmitted Reflecting on Two Years of Professorship as a story · 2 points
HN discussionSubmitted A Call to Build Models Like We Build Open-Source Software as a story · 2 points
HN discussionSubmitted The Lakh MIDI Dataset v0.1 as a story · 2 points
HN discussionSubmitted A Call to Build Models Like We Build Open-Source Software as a story · 1 points
HN discussionSubmitted A Year at Google Brain's Residency Program as a story · 1 points
HN discussion
