Explained to your Grandma
Quentin Fayet
"Field of study that gives computers the ability to learn without being explicitly programmed"
- Arthur Samuel
Based of mathematical fields of study :
Resolving problems where human brain is not enough efficient.
Inputs
Trained model
Outputs
Mathematical law / abstraction of a problem
Measurable property contained into an input
Machine Learning algorithms belong to different families :
Machine Learning
Deep Learning
Attempt to provide high-level abstractions of the data
One of the most important thing to do before using machine learning is to visualize the data.
Dataviz(ualization) is almost a science itself.
Visualization of 2D/3D data is easy. What about 100D data ?
Specialized languages :
Languages and libraries :
https://coursera.org/learn/machine-learning
https://www.youtube.com/playlist?list=PLZSO_6-bSqHQCIYxE3ycGLXHMjK3XV7Iz
Available at my desk :