News for hackers. Stuff that matters.

vkhuc

vkhuc on Hacker News

Re:Google Dataset Search on Thursday May 06, 2021 @07:06PM (#27070002)
Absolutely. This dataset search was first introduced in September of 2018. It was out of beta in January last year: https://www.kdnuggets.com/2020/01/google-dataset-search.html.
Re:Obstacles on the Path to AI on Thursday October 22, 2015 @09:40PM (#10436330)
Thanks. That's the book I'm reading :)
Re:Obstacles on the Path to AI on Thursday October 22, 2015 @07:01PM (#10435741)
Although I'm working on deep neural nets, this material is too advanced to me. Looks like deep nets + bayesian reasoning is the next big thing.
Re:Curated list of speech and natural language processing resources on Thursday October 01, 2015 @01:52PM (#10313049)
Why use NLTK when we can use spaCy instead? http://spacy.io/
Re:SpaCy: Industrial-strength NLP with Python and Cython on Sunday January 25, 2015 @01:04PM (#8943605)
Nice. As a guy who got involved into OpenNLP's development, I'd like to see the comparison too.

Also, it would be great if you include SENNA into your benchmark: http://ml.nec-labs.com/senna/

Re:Nvidia's demo of real-time object recognition using deep learning [... on Thursday January 08, 2015 @02:58PM (#8858557)
I think they used the methods described in http://www.cs.berkeley.edu/~rbg/papers/r-cnn-cvpr.pdf
Re:Twitter Natural Language Processing on Wednesday October 22, 2014 @04:24PM (#8494906)
I've been looking at Factorie for a while but haven't actually done anything heavy with it.

I planned to replace the optimizer in CMU's POS tagger with the one implemented in OpenNLP to make the tagger fully Apache. Unfortunately, so busy right now. Currently, I'm running the tagger on AWS, so the GPL doesn't hurt me much.

BTW, besides the POS tagger, CMU's TweeboParser depends on Turbo Parser which again is licensed under GPL.

Re:Twitter Natural Language Processing on Tuesday October 21, 2014 @11:54PM (#8491410)
Yes, Noah Smith's NLP group at CMU is awesome. Btw, Noah is moving to UWash.
Re:Twitter Natural Language Processing on Tuesday October 21, 2014 @11:45PM (#8491401)
The whole project is based on various libraries. In particular, the POS tagger itself uses the OWLQN optimizer from Stanford NLP (licensed under GPL).

However, it's possible to remove GPL libraries out of the POS tagger as mentioned here: https://github.com/brendano/ark-tweet-nlp/blob/master/LICENS...

Re:Twitter Natural Language Processing on Tuesday October 21, 2014 @05:33PM (#8490199)
Great, I've been waiting for the release of TweeboParser. Just before EMNLP14 gets started.
Re:Level-Up Your Machine Learning on Monday July 21, 2014 @08:30PM (#8066852)
There are some (free) good books that haven't been mentioned yet:

1) "Data Mining and Analysis: Fundamental Concepts and Algorithms" by Zaki and Meira http://www.cs.rpi.edu/~zaki/PaperDir/DMABOOK.pdf

This book covers many ML topics with concrete examples.

2) "Computer Vision: Models, Learning, and Inference" by Simon Prince: http://web4.cs.ucl.ac.uk/staff/s.prince/book/book.pdf

Despite a CV book, the first half of it is like a statistics book that comes with examples in CV which are very easy to follow.

Re:Level-Up Your Machine Learning on Monday July 21, 2014 @08:20PM (#8066812)
I skimmed over Mohri's book and I think the topics it covers are quite narrow.

For mathematical foundations of ML, I would recommend the book "Understanding Machine Learning: From Theory to Algorithms" by Shai Shalev-Shwartz.

A brief version of the book is available to download on the author's website: http://www.cs.huji.ac.il/~shais/Handouts.pdf

Older ยป