Tag: survey

Excellent thread about GAN progress, read! 👇 https://t.co/rKRVWbytcX

— Denny Britz (@dennybritz) January 18, 2019

“Estimating the absolute performance of a model is probably one of the most challenging tasks in machine learning.” A great read on a foundational and oft neglected topic. I learned stuff. https://t.co/VmKpbxvqWu

— Brandon Rohrer (@_brohrer_) January 17, 2019

Exploratory Design in #datavisualization, which I offer up as a way to concretize iterative approaches by better understanding chart similarity and using techniques from exploratory data analysis in the production of explanatory data visualization.https://t.co/vIN6aSS4Iv

— Elijah Meeks (@Elijah_Meeks) January 15, 2019

😰 Totally not cramming for TAing by reviewing @theotheredgar's slides from SDSS...
🐘 "Big Data with R" https://t.co/labThUnVkO #rstats #sparklyr #dplyr pic.twitter.com/TsgMuwYhTC

— Mara Averick (@dataandme) January 15, 2019

Take a sneak peek into TensorFlow 2.0’s new features!

Learn more here ↓ https://t.co/NQAsvxT9g2

— TensorFlow (@TensorFlow) January 14, 2019

If you're interested in interpretability and better understanding #NLProc models 🔎, read this excellent TACL '19 survey by @boknilev. Clearly covers important research areas.
Paper: https://t.co/NPhA4UaUwC
Appendix (categorizing all methods): https://t.co/a8mFNzNd7i

— Sebastian Ruder (@seb_ruder) January 11, 2019

I expected the Transformer-based BERT models to be bad on syntax-sensitive dependencies, compared to LSTM-based models.

So I run a few experiments. I was mistaken, they actually perform *very well*.

More details in this tech report: https://t.co/6hV9YoOvN8 pic.twitter.com/O0YwRnp7QH

— (((ل()(ل() 'yoav)))) (@yoavgo) January 6, 2019

"Modern Deep Learning Techniques Applied to NLP"

An up-to-date learning resource that integrates important information related to NLP research, such as: SoTA, emerging concepts, applications, benchmark, datasets, code etc.https://t.co/aYRavEuup3 pic.twitter.com/tbosUGslq8

— ML Review (@ml_review) January 2, 2019

One last blog post before the new year:

A Tutorial on Uncertainty: what it is, how to measure it, and how to use these measures to do useful things. https://t.co/3OGwEq4Sze pic.twitter.com/xvRj2HInkX

— Eric Jang (@ericjang11) December 28, 2018

ML Breakthroughs in 2018 & Trends for 2019: Comprehensive article by @AnalyticsVidhya about highlights in NLP, CV, and more with predictions by @StackNet_, @xsteenbrugge, and mehttps://t.co/mie1y1E2xo

— Sebastian Ruder (@seb_ruder) December 21, 2018

Very nice review of the literature on human statistical learning. The surprising conclusion? Chunk-learning, rather than transitional probability tracking, best describes human performance. https://t.co/xHgr6bszwc

— Michael C. Frank (@mcxfrank) December 21, 2018

My last paper for 2018: A brief history of forecasting competitions https://t.co/dsROdr8iQA #forecasting

— Rob J Hyndman (@robjhyndman) December 21, 2018