Radim Řehůřek
@RadimRehurek
Applied #MachineLearning, #NLP, #DeepLearning. I like to build practical software. PhD in CS. Founder @RaReTechTeam. Creator @gensim_py. Life in SEA 
(
).
Txioak
- Txioak, current page.
- Txioak eta erantzunak
- Media
You blocked @RadimRehurek
Are you sure you want to view these Tweets? Viewing Tweets won't unblock @RadimRehurek
-
Finkatutako Txioa
Scoping and research analysis finished, starting R&D on real data.pic.twitter.com/C6L98dmqQP
Milesker. Twitterrek zure denbora lerroa hobetzeko erabiliko du hau. Desegin -
DeepMind tackles another AI barrier: internal environment simulation. Next up in the GAI quest: simulation of self?https://twitter.com/DeepMindAI/status/888001924645236736 …
Milesker. Twitterrek zure denbora lerroa hobetzeko erabiliko du hau. Desegin -
Radim Řehůřek(e)k Bertxiotua
Scalnet (keras api in scala) will be more usable next release: https://github.com/deeplearning4j/ScalNet/blob/master/src/test/scala/org/deeplearning4j/scalnet/examples/keras/convolution/LeNetMnistExample.scala … great job
@maxpumperla !Milesker. Twitterrek zure denbora lerroa hobetzeko erabiliko du hau. Desegin -
Radim Řehůřek(e)k Bertxiotua
The LSTM Strikes Back: sub 60 perplexities on LM PTB (single model). All you need is a (well tuned) LSTM :) https://arxiv.org/abs/1707.05589 pic.twitter.com/V7nh3dsoPd
Milesker. Twitterrek zure denbora lerroa hobetzeko erabiliko du hau. Desegin -
Radim Řehůřek(e)k Bertxiotua
A call for "engineering corpus", to train domain-specific
#word2vec models on. Do you know such corpus? Please RT.https://groups.google.com/d/msg/gensim/k7xSdLDVTHk/HR5pts4IBQAJ …Milesker. Twitterrek zure denbora lerroa hobetzeko erabiliko du hau. Desegin -
A new way to evaluate topic models like LDA: topic intrusion in docs, instead of word intrusion in topics
https://arxiv.org/abs/1706.05140 pic.twitter.com/QM0alswirw
Milesker. Twitterrek zure denbora lerroa hobetzeko erabiliko du hau. Desegin -
Radim Řehůřek(e)k Bertxiotua
Introducing Facets, an open source visualization tool to help understand and analyze
#MachineLearning datasets http://goo.gl/T78rnu pic.twitter.com/zJ0HuAZFVAMilesker. Twitterrek zure denbora lerroa hobetzeko erabiliko du hau. Desegin -
Radim Řehůřek(e)k Bertxiotua
Thrilled to give a keynote on my fav topic at
#PyData Warsaw in October: Building practical#ML systems
pic.twitter.com/E8Jjor1LGr
Milesker. Twitterrek zure denbora lerroa hobetzeko erabiliko du hau. Desegin -
The old curmudgeon has a point though! Just his definition of "life" is too humane and constraining for the voracious AI crowd.https://twitter.com/ageitgey/status/885598368566607872 …
Milesker. Twitterrek zure denbora lerroa hobetzeko erabiliko du hau. Desegin -
Radim Řehůřek(e)k Bertxiotua
Learn
#gensim &#NLProc tricks from our#opensource developer@menshikh_iv at@PyConRu this Sunday!
http://pycon.ru/2017/en/program/content/menshih/ …Milesker. Twitterrek zure denbora lerroa hobetzeko erabiliko du hau. Desegin -
Radim Řehůřek(e)k Bertxiotua
This is cool. An adversarial attack libraryhttps://twitter.com/arxiv_cscv/status/885720644314210305 …
Milesker. Twitterrek zure denbora lerroa hobetzeko erabiliko du hau. Desegin -
Already anticipating the startup pitches here
"Instagram Democratized"? "MeUndies for Art"?https://twitter.com/Md_Harris/status/885584627490050048 …
Milesker. Twitterrek zure denbora lerroa hobetzeko erabiliko du hau. Desegin -
Radim Řehůřek(e)k Bertxiotua
I would love to get some feedback from datascientists / kagglers with an extensive experience of feature binning:https://github.com/scikit-learn/scikit-learn/pull/7668 …
Milesker. Twitterrek zure denbora lerroa hobetzeko erabiliko du hau. Desegin -
Radim Řehůřek(e)k Bertxiotua
Python Implementation of the paper (http://johanneskopf.de/publications/pixelart/ …) "Depixelizing Pixel Art": https://github.com/vvanirudh/Pixel-Art …pic.twitter.com/2JKpBmeo6s
Milesker. Twitterrek zure denbora lerroa hobetzeko erabiliko du hau. Desegin -
Radim Řehůřek(e)k Bertxiotua
"TextExt - DBpedia Open Extraction Challenge" http://wiki.dbpedia.org/textext
Milesker. Twitterrek zure denbora lerroa hobetzeko erabiliko du hau. Desegin -
Radim Řehůřek(e)k Bertxiotua
NoScope: 1000x Faster Deep Learning Queries over Video http://dawn.cs.stanford.edu/2017/06/22/noscope/ …pic.twitter.com/Y4mE2DZJpB
Milesker. Twitterrek zure denbora lerroa hobetzeko erabiliko du hau. Desegin -
Wow, neat extension of the "hashing trick"! Clean and simple idea for Bloom embeddings by
@serrjoa HT@fastml_extra https://arxiv.org/abs/1706.03993 pic.twitter.com/zQ0R5QqE3q
Milesker. Twitterrek zure denbora lerroa hobetzeko erabiliko du hau. Desegin -
Radim Řehůřek(e)k Bertxiotua
"When not to use deep learning" -- Great article!http://hyperparameter.space/blog/when-not-to-use-deep-learning/ …
Milesker. Twitterrek zure denbora lerroa hobetzeko erabiliko du hau. Desegin -
Radim Řehůřek(e)k Bertxiotua
What are some things you can do to optimize for iteration speed?https://erikbern.com/2017/07/06/optimizing-for-iteration-speed.html …
Milesker. Twitterrek zure denbora lerroa hobetzeko erabiliko du hau. Desegin -
Radim Řehůřek(e)k Bertxiotua
TFW a new contributor does an amazing job, fixing a long standing issue
Congrats and big thanks to @messrs_puchu!https://github.com/RaRe-Technologies/gensim/pull/1442 …Milesker. Twitterrek zure denbora lerroa hobetzeko erabiliko du hau. Desegin -
For the impatient: direct links to the
#NLP datasets (text similarity, entailment, paraphrasing…)https://github.com/facebookresearch/SentEval/blob/master/data/get_transfer_data.bash …Milesker. Twitterrek zure denbora lerroa hobetzeko erabiliko du hau. Desegin
Badirudi kargak luze hartuko duela.
Baliteke Twitterren kapazitatez gaindi egotea edo momentuko gainkarga bat izatea. Berriro saiatu edo Twitterren Egoera ikusi informazio gehiagorako.
