January 2019 - Bag of Tricks in Machine Learning

CV papers

January 31, 2019January 31, 2019 by admin

https://github.com/hoya012/deep_learning_object_detection

Ground truth?

January 31, 2019January 31, 2019 by admin

If you want to question whether human-produced labels for training ML models represent "ground truth," look no further than the sheer volume of misclassifications in a pair of recycling/trash bins.
— Sean J. Taylor (@seanjtaylor) January 29, 2019

To read more books and less paper

January 27, 2019January 27, 2019 by admin

CMU 10-708 PGM by Eric Xing

January 27, 2019January 27, 2019 by admin

https://www.youtube.com/channel/UCim-E6bNz7lUyKZwhgN6S1A/videos

How to Structuring Python Project

January 27, 2019January 27, 2019 by admin

https://docs.python-guide.org/writing/structure/

Fast ai course v3

January 26, 2019January 26, 2019 by admin

https://course.fast.ai/

Natural Questions Corpus (Google AI)

January 25, 2019January 25, 2019 by admin

https://ai.googleblog.com/2019/01/natural-questions-new-corpus-and.html

在文本分类任务中，有哪些论文中很少提及却对性能有重要影响的tricks？

January 24, 2019January 24, 2019 by admin

https://www.zhihu.com/question/265357659

把Cross Entropy梯度分布拉‘平’ – AAAI 2019 Oral

January 23, 2019January 23, 2019 by admin

AAAI 2019 Oral | 把Cross Entropy梯度分布拉‘平’，就能轻松超越Focal Loss
https://www.jiqizhixin.com/articles/2019-01-17-30

Kaggle Mercari Price Suggestion Challenge (1 place) — Pawel Jankiewicz, Konstantin Lopuhin

January 22, 2019January 22, 2019 by admin

Shujian 🍱Follow

Retweet on Twitter Shujian 🍱 Retweeted

Ves Stoyanov @vesko_st·

Our system, RoBERTa just topped the GLUE leaderboard. When trained with the right recipe, BERT still shows state-of-the-art results. Great collaboration from our team at Facebook AI @facebookai! https://t.co/RPPlCL1UfU

Reply on Twitter 1152024598981906432 Retweet on Twitter 11520245989819064327 Like on Twitter 115202459898190643248 Twitter 1152024598981906432

Retweet on Twitter Shujian 🍱 Retweeted

Facebook AI@facebookai·

Congrats to our AI team for matching the top GLUE benchmark performance! We believe strongly in open & collaborative research and thank @GoogleAI for releasing BERT. It led to RoBERTa, our robustly optimized system that was trained longer, on more data. https://t.co/FAKAGboEHl

Reply on Twitter 1151991448654340097 Retweet on Twitter 1151991448654340097103 Like on Twitter 1151991448654340097447 Twitter 1151991448654340097

Retweet on Twitter Shujian 🍱 Retweeted

Sebastian Raschka @rasbt·

"Awesome Graph Classification" -- A collection of graph classification methods, covering embedding, deep learning, graph kernel, and factorization papers with reference implementations https://t.co/ugpL3xSvf1

Reply on Twitter 1151047581151240192 Retweet on Twitter 1151047581151240192303 Like on Twitter 1151047581151240192991 Twitter 1151047581151240192

Shujian 🍱@Shujian_Liu·

lol https://t.co/LCsmd6C2SF

Reply on Twitter 1151694837793591296 Retweet on Twitter 1151694837793591296 Like on Twitter 1151694837793591296 Twitter 1151694837793591296

Retweet on Twitter Shujian 🍱 Retweeted

Brenden Lake @LakeBrenden·

I believe that perfect autonomous driving will be impossible until we build machines with intuitive psychology.

"Developing software that can reliably anticipate what other drivers, pedestrians and cyclists are going to do, will be much more difficult."
https://t.co/EHAYee1rRm

Reply on Twitter 1151474001597915136 Retweet on Twitter 115147400159791513618 Like on Twitter 115147400159791513691 Twitter 1151474001597915136