🔥Telegram İfşa

"Applications of Deep Neural Networks" [569 pages] 📚by jeffheaton pdf arxiv.org/pdf/2009.05673… abs arxiv.org/pdf/2009.05673…

We present SR3: a conditional diffusion model for image super-resolution. SR3's face super resolution results are extremely hard to distinguish from real images, reaching an ideal confusion rate of 50% in human evaluation. iterative-refinement.github.io arxiv.org/abs/2104.07636

Entropic Out-of-Distribution Detection #IJCNN2021 By David Macêdo, PhD Ing Ren Tsang IsoMax - SoftMax drop-in replacement - SoTA on Out-of-Distribution - No accuracy drop - No efficiency drop - No hyperparams abs arxiv.org/abs/1908.05569 code github.com/dlmacedo/entro…

Excited to announce Dodrio, an interactive visualization tool designed to help NLP researchers and practitioners analyze and compare attention weights in transformer-based models with linguistic knowledge! Try Dodrio in your browser: poloclub.github.io/dodrio/ #ACL2021NLP #NLProc

From DNA to protein folding and alphafold2 Tutorial by Nikolas Adaloglou (black0017) Covers all biology aspects required to grasp AlphaFold2 theaisummer.com/deep-learning-…

An Elementary Introduction to Information Geometry Survey by Frank Nielsen [2020, 56 pp] - Basics of Differential Geometry - Information Manifolds - Applications abs arxiv.org/abs/1808.08271 pdf arxiv.org/pdf/1808.08271…

The Roadmap of Mathematics for Machine Learning By Tivadar Danka tivadardanka.com/blog/roadmap-o…

"Deep Learning for Molecules and Materials. 2021" Online book by Andrew White 🐦‍⬛ dmol.pub

glum - fast, maintainable, Python-first library for fitting GLMs with an extensive feature set. By Ben Thompson -L1/L2/Tichonov –Normal,Poisson,Tweedie etc –Box/linear inequality constraints,sample weights, offsets –scikit-learn compatible github.com/Quantco/glum

Bayesian Modeling and Computation in Python Online Book by aloctavodia.bsky.social RavinKumar @junpenglao Powered by Jupyter Book bayesiancomputationbook.com/welcome.html

Close The Sky Over Ukraine

🔮Nixtla - Forecasting Pipeline as a Service By @fede_gr – 25% better accuracy than Amazon Forecast – 20% more accurate than fbprophet – 4x faster than Amazon Forecast & less expensive github.com/Nixtla/nixtla

Pen and Paper Exercises in Machine Learning by Michael U. Gutmann arxiv.org/abs/2206.13446 kudos to the author for putting these online -- surely will be a valuable resource for educators of all stripes (but especially for TAs and those who teach privately).

"Stanford CS25 - Transformers United" Seminar by FTP Mark Chen Lucas Beyer (bl16) Aditya Grover Barret Zoph Drew Jaegle Aidan Gomez Chris Olah Geoffry Hinton Covers Transformers in Language, Vision, Decision-Making, Audio youtube.com/playlist?list=…

"The Little Book of Deep Learning" 140 pp📖 Book by François Fleuret 🫡 fleuret.org/public/lbdl.pdf