MACHINE LEARNING CAPABILITIES FOR MOBILE APPS
Machine Learning is:
a way to give “computers the ability to learn without being explicitly programmed.”
- Product Personalization
- Loyalty Programs
- Next Best Offer
- Customer Churn
- Fraud Detection
- Insurance Pricing
- Stock Trading
Wield this power or it will wield you
install a ton of surveillance cameras
get really good at ml-powered facial recognition
match faces to IDs
monitor emotions...and manipulate them
invisibly track location
Scary uses of ML
"A computer program is said to learn from experience E with respect to some class of tasks T and performance measure P if its performance at tasks in T, as measured by P, improves with experience E.” (Tom Mitchell, 1997).
How to make a machine learn*
Gather a lot of data (text,images, sounds)
Divide that data into a training set and a test set
- The training set is categorized (sorted by hand or by machine)
- The test set is uncategorized
Use an algorithm to train a model with the training set by pairing input with expected output
Use the test set to test the accuracy of the training
rinse & repeat
Machine Learning is Easy!
DIY Machine Learning is hard
you need a lot of firepower & skillz
Let's leverage the cloud!
Let's build something!
Rich, animated, “no compromise” native UI
(with shared UI code)
in the iOS App Store or Google Play to try this app out for yourself.
Maximum code and skill reusability
ML for mobile apps
By Ignacio Fuentes