This talk discusses Google Brain's Magenta, a project using TensorFlow to generate art and music.
The slides are adapted from Douglas Eck's talk at Google I/O 2017 (https://www.youtube.com/watch?v=2FAjQ6R_bf0)
Music and Art with Machine Learning | GDG DevFest Bangkok 2017 (Oct 7th, 2017)
1. Music and Art
with Machine Learning
Part I
Ta Virot Chiraphadhanakul (@tvirot)
Google Developer Expert in Machine Learning
Managing Director, Skooldio
13. Machine Learning on Google Cloud Platform
Pre-trained ML models Custom ML models
14. Understand the content of images
● Label Detection
● Optical Character Recognition
● Explicit Content Detection
● Face Detection
etc.
Google Cloud
Vision API
Photos: Google Cloud Platform / Kaz Sato
@tvirot
23. Autoencoders
● A neural network with the target values set to be equal
to the inputs
● The goal is to learn an approximation to the identity
function -- a lower-dimensional feature representation
● By placing constraints on the network, such as by
limiting the number of hidden units, we can discover
interesting structure about the data
25. Sequence Models
● Data points are related or dependent on each other
(e.g., text, audio waves, videos)
● Challenges:
○ Order matters
○ Statistical Invariance
○ Long-term dependencies