EPISODE · Aug 31, 2018 · 45 MIN
C Programming for Machine Learning (LIVE)
from Siraj Raval
The ability to write implementations of machine learning algorithms in pure C allows developers to very efficiently manage memory allocation, concurrency, and control flow. That means fast implementations that can outperform preexisting models in other languages, including even (gasp) Python. It’s a useful skill to know and in this live stream I’ll use C and C-based Python tools like Cython + spaCy to develop some really fast natural language processing algorithms for text data. We’ll be able to tokenize, tag, normalize, vectorize, and dependency parse articles of text to derive valuable insights. No installation necessary, we'll do this together using Google Colab in the browser. Join me, there’s a lot to cover here! Code for this video: https://github.com/llSourcell/c_programming_for_machine_learning Please Subscribe! And like. And comment. That's what keeps me going. Want more education? Connect with me here: Twitter: https://twitter.com/sirajraval Facebook: https://www.facebook.com/sirajology instagram: https://www.instagram.com/sirajraval This video is apart of my Machine Learning Journey course: https://github.com/llSourcell/Machine_Learning_Journey More learning resources: https://pydata.org/berlin2016/schedule/presentation/51/ https://smerity.com/articles/2018/cython_for_high_and_low.html https://explosion.ai/blog/writing-c-in-cython https://spacy.io/api/cython https://medium.com/huggingface/100-times-faster-natural-language-processing-in-python-ee32033bdced Join us in the Wizards Slack channel: http://wizards.herokuapp.com/ Learn more about the School of AI: https://www.theschool.ai And please support me on Patreon: https://www.patreon.com/user?u=3191693
What this episode covers
The ability to write implementations of machine learning algorithms in pure C allows developers to very efficiently manage memory allocation, concurrency, and control flow. That means fast implementations that can outperform preexisting models in other languages, including even (gasp) Python. It’s a useful skill to know and in this live stream I’ll use C and C-based Python tools like Cython + spaCy to develop some really fast natural language processing algorithms for text data. We’ll be able to tokenize, tag, normalize, vectorize, and dependency parse articles of text to derive valuable insights. No installation necessary, we'll do this together using Google Colab in the browser. Join me, there’s a lot to cover here! Code for this video: https://github.com/llSourcell/c_programming_for_machine_learning Please Subscribe! And like. And comment. That's what keeps me going. Want more education? Connect with me here: Twitter: https://twitter.com/sirajraval Facebook: https://www.facebook.com/sirajology instagram: https://www.instagram.com/sirajraval This video is apart of my Machine Learning Journey course: https://github.com/llSourcell/Machine_Learning_Journey More learning resources: https://pydata.org/berlin2016/schedule/presentation/51/ https://smerity.com/articles/2018/cython_for_high_and_low.html https://explosion.ai/blog/writing-c-in-cython https://spacy.io/api/cython https://medium.com/huggingface/100-times-faster-natural-language-processing-in-python-ee32033bdced Join us in the Wizards Slack channel: http://wizards.herokuapp.com/ Learn more about the School of AI: https://www.theschool.ai And please support me on Patreon: https://www.patreon.com/user?u=3191693
NOW PLAYING
C Programming for Machine Learning (LIVE)
No transcript for this episode yet