Tag: learning

The FAIR folks have a brand new course on #DeepLearning and #PyTorch on @udacity. https://t.co/DaxYWNy393 pic.twitter.com/tc5Gz1UafV

— Delip Rao (@deliprao) November 9, 2018

Slowly but surely, deep learning is joining the last domain to resist it, tabular data. The networks are still relatively simple which makes me think we need better primitives for structured data. What is the convolution equivalent for spreadsheets? https://t.co/9gjCcNOdsG pic.twitter.com/4DBDrSBoeQ

— Emmanuel Ameisen (@EmmanuelAmeisen) November 9, 2018

Everything you wanted to know about the effects of batch size on neural net training behavior but were afraid to ask!

Measuring the Effects of Data Parallelism on Neural Network Training
Chris Shallue, Jaehoon Lee, Joe Antognini,  @jaschasd, Roy Frostig, George Dahl @GoogleAI https://t.co/6TUbthAfai

— Jeff Dean (@JeffDean) November 9, 2018

This is stunning work from @dcpage3, who has smashed our DAWNBench CIFAR10 training record, and written a fascinating and detailed series explaining all the improvements he made.

All researchers interested in model speed or accuracy need to read this!https://t.co/pd6oJhqfX9

— Jeremy Howard (@jeremyphoward) November 8, 2018

Sources Of Uncertainty https://t.co/eZ2bbpDzwV pic.twitter.com/qdL61TNqxA

— Chris Albon (@chrisalbon) November 8, 2018

Python, NLTK, and the Digital Humanities: Finding Patterns in Gothic Literature by @eleanorstrib https://t.co/fb16KpCCJd

— Rachel Thomas (@math_rachel) November 8, 2018

New post on my #EMNLP2018 Highlights: Inductive bias, cross-lingual learning, and morehttps://t.co/IrqcZaQ8rM

— Sebastian Ruder (@seb_ruder) November 7, 2018

New #tidytuesday screencast, analyzing data on US wind power 🌬️. Watch me realize I don't know how to use the new gganimate API 😱https://t.co/XIcJwgeNPq #rstats pic.twitter.com/KnujKXF5LA

— David Robinson (@drob) November 6, 2018

The Marauder’s map I presented at AISec just went up on arXiv (links below). The talk analyzed current ML security and privacy research through the lens of Saltzer and Schroeder’s principles (introduced in 1975!) to identify directions for future research. Here is a summary: pic.twitter.com/SQ1d9KqBqB

— Nicolas Papernot (@NicolasPapernot) November 6, 2018

PDF versions of brilliant #MachineLearning cheatsheets covering the content of Stanford's CS 229 class: https://t.co/1rjJ5gkiyX by @afshinea

Class website: https://t.co/eapxOqdDqO#BigData #DataScience #AI #DeepLearning #NeuralNetworks #DataLiteracy #DataScientists pic.twitter.com/K2jQniSqZ5

— Kirk Borne (@KirkDBorne) November 6, 2018

BlackBox NLP 2018 slides: https://t.co/DL0smjHchA

— (((ل()(ل() 'yoav)))) (@yoavgo) November 5, 2018

New blog post on "The Three Ds of Machine Learning Systems Design" https://t.co/sfIoszOIzJ

— Neil Lawrence (@lawrennd) November 5, 2018