tensorflow-for-deep-learnin.../Papers/Adversarial_examples_1607.02533v1.md
2016-07-23 17:09:05 -07:00

8 lines
494 B
Markdown

# Intro
* Predictive or Supervised: learn a mappping from inputs x to outputs u, given a labeled set of input-output paris (the training set).
- The training input x_i is called features, attributes, covariates.
- If y_i assumes a value from a finite set, it's called categorical or nominal, and the problem is classification or pattern recognition. If y_i us real-valued scalar, it is regression.
* Descriptive or unsupervised learning: find patterns in the data (knowledge discovery). c