Pragmatic Machine Learning RARE Technologies Navigation
  • Services
  • Products
    • PII Tools
  • Corporate Training
    • Overview
    • Python Best Practices
    • Practical Machine Learning
    • Topic Modelling
    • Deep Learning in Practice
  • For Students
    • Open source
    • Incubator
    • Competitions
  • Company
    • Careers
    • Our Team
  • Blog
  • Contact
  • Search
  • Services
  • Products
    • PII Tools
  • Corporate Training
    • Overview
    • Python Best Practices
    • Practical Machine Learning
    • Topic Modelling
    • Deep Learning in Practice
  • For Students
    • Open source
    • Incubator
    • Competitions
  • Company
    • Careers
    • Our Team
  • Blog
  • Contact
  • Search

Tag Archive

Below you'll find a list of all posts that have been tagged as “word2vec”

Word2vec in Python, Part Two: Optimizing

Radim Řehůřek 2013-09-21 gensim, programming 46 Comments

Last weekend, I ported Google’s word2vec into Python. The result was a clean, concise and readable code that plays well with other Python NLP packages. One problem remained: the performance was 20x slower than the original C code, even after all the obvious NumPy optimizations.

BLASoptimizationword2vec

Deep learning with word2vec and gensim

Radim Řehůřek 2013-09-17 gensim, programming 33 Comments

Neural networks have been a bit of a punching bag historically: neither particularly fast, nor robust or accurate, nor open to introspection by humans curious to gain insights from them. But things have been changing lately, with deep learning becoming a hot topic in academia with spectacular results. I decided to check out one deep learning algorithm via gensim.

gensimword2vec
  • Page 2 of 2
  • ←
  • 1
  • 2

STAY AHEAD OF THE CURVE

Get our latest tutorials, updates and insights delivered straight to your inbox.

1-2 times a month, if lucky. Your information will not be shared.
  • Services
  • Careers
  • Our Team
  • Corporate Training
  • Blog
  • Incubator
  • Contact
  • Competitions
  • Site Map
RARE Technologies
[email protected]
Světova 5, Prague, Czech Republic