What Makes a Good Feature? - Machine Learning Recipes #3

Channel:
United States Google for Developers
Subscribers:
2,520,000
Published on ● Video Link: https://www.youtube.com/watch?v=N9fDIAflCMY


Duration: 5:41
519,232 views
6,250

Good features are informative, independent, and simple. In this episode, we'll introduce these concepts by using a histogram to visualize a feature from a toy dataset. Updates: many thanks for the supportive feedback! I’d love to release these episodes faster, but I’m writing them as we go. That way, I can see what works and (more importantly) where I can improve.

We've covered a lot of ground already, so next episode I'll review and reinforce concepts, introduce clearer syntax, spend more time on testing, and continue building intuition for supervised learning.

I also realize some folks had dependency bugs with Graphviz (my fault!). Moving forward, I won't use any libraries not already installed by Anaconda or Tensorflow.

Last: my code in this cast is similar to these great examples. You can use them to produce a more polished chart, if you like:

http://matplotlib.org/examples/statistics/histogram_demo_multihist.html

Follow https://twitter.com/random_forests for updates on new episodes!

Subscribe to the Google Developers: http://goo.gl/mQyv5L -
Subscribe to the brand new Firebase Channel: https://goo.gl/9giPHG
And here's our playlist: https://goo.gl/KewA03



Other Videos By Google for Developers


2016-05-06The Developer Show (TL;DR 025)
2016-05-05Understanding GCM on iOS, Part 2: GCM (Route 85)
2016-05-04#Love4Dev - Seeing what others create in web development with Paul Lewis
2016-05-02Google Developers Africa On Air: REST matters (and you need more of it)
2016-05-02#Love4Dev - Solving life-changing puzzles with Colt McAnlis
2016-04-29The Developer Show (TL;DR 024)
2016-04-28Enterprise SSO with Chrome Custom Tabs
2016-04-28AdMob Banner Ads - Mobile Ads Garage #2
2016-04-27#Love4Dev - Developing for Android with Rich Hyndman
2016-04-27#Love4Dev - Working together in web with Rob Dodson
2016-04-27What Makes a Good Feature? - Machine Learning Recipes #3
2016-04-26In-App Billing Security - The Zen of Monetization #8
2016-04-25#Love4Dev - Using the open web for simple solutions with Paul Kinlan
2016-04-22The Developer Show (TL;DR 023)
2016-04-22#Love4Dev - Using the Android Platform to transform your ideas into reality with Joanna Smith
2016-04-20#Love4Dev - Android's open ecosystem with Fred Sauer
2016-04-20Maps APIs - Best Practices
2016-04-19Implementing Android In-App Billing - The Zen of Monetization #7
2016-04-18#Love4Dev - What Magnus Hyttsten loves most about the power of mobile APIs
2016-04-15The Developer Show (TL;DR 022)
2016-04-14Learn about Android Development Patterns over Coffee with Joanna Smith - Coffee with a Googler


Tags:
machine learning
machine learning recipes
machine learning features
binary classification
independent features
machine learning algorithms
how to pick good features
machine learning examples
introduction to machine learning
machine learning projects
product: web
Fullname: Josh Gordon
Location: NYC
Other: NoGreenScreen
GDS: Full Production
Type: Other
Team: Scalable Advocacy
machine learning tutorial