Intro

Andreas Mueller NYU Center for Data Science

Clone this repository:

https://github.com/amueller/advanced_training

Schedule

Start: 9am End: 5pm

Lunch: ~11:45am Snack: ~3pm

Outline

1 Basic algorithms

• Review of supervised learning
• Linear models for classification and regression
• Loss functions, regularization, empirical risk minimization
• Path algorithms

2 Preprocessing

• Scaling and normalization
• Continuous and discrete features
• Feature selection
  • Univariate
  • Model-based
  • RFE
  • Forward / backward selection
• Polynomial and interaction features

3 Basic tools

• Cross-validation vs train/test split
• GridSearchCV
• Overfitting Parameters
• Scoring Metrics

4 Advanced Supervised Learning

• Decision Tree Recap
• Random Forests
• Gradient Boosting / xgboost
• Kernel SVMs
• Kernel approximation
• Neural Networks

5 Advanced tools

• Pipelines
• FeatureUnion
• Function Transformer

6 Unsupervised feature extraction and visualization

• PCA
• NMF
• Robust PCA
• TSNE

7 Outlier Detection

• Elliptic Envelope
• IForest
• KDE
• robust PCA

8 Gaussian Processes

9 beyond standard sklearn

• out of core
• custom estimators