机器学习新方法

1. Cost-Sensitive Multi-Class Classification

Cost-sensitive multi-class classification is a problem related to multi-class classification, in which instead of there being one or more “correct” labels for each observation, there is an associated vector of costs for labeling each observation under each label, and the goal is to build a classifier that predicts the class with the minimum expected cost.
https://nbviewer.org/github/david-cortes/costsensitive/blob/master/example/costsensitive_multiclass_classification.ipynb
https://github.com/lilelr/costsensitive

2. stand deviation
   https://en.wikipedia.org/wiki/Standard_deviation

3. Non-negative least squares
   In mathematical optimization, the problem of non-negative least squares (NNLS) is a type of constrained least squares problem where the coefficients are not allowed to become negative.

4. machine-learning-neural-networks-scikit-learn https://www.pluralsight.com/guides/machine-learning-neural-networks-scikit-learn