T81-574: Foundations of Analytics

Topics

1. Introduction to data science/analytics

   1. Linear algebra review
   2. Python environment setup

2. Statistical Description of Structured Data

   1. Introduction to statistics: random variables, random distribution, histogram
   2. Statistic distributions: Gaussian, Poisson etc.

3. Linear model

   1. Correlation;
   2. Linear regression;
   3. Likelihood function and maximum likelihood estimator

4. Logistic regression and Poisson regression

   1. Logistic regression
   2. Newton-raphson method and Gradient Descent
   3. Poinsson regression

5. Generalized Linear Model

   1. Exponential Family
   2. Link function
   3. Generalized Linear Model

6. Statistical Modeling Framework

   1. Empirical Modeling Practices
   2. Feature engineer, variable selection
   3. Model evaluations

7. Machine Learning I: Tree Algorithms

   1. CART Model
   2. Entropy and impurity measure
   3. Random forest and GBM

8. Machine Learning II

   1. Artificial neurons, activation function
   2. Feedforward neural networks
   3. Stochastic gradient descent
   4. Backpropagation

9. Nature Language Process I

   1. Word2vec; embeddings
   2. Word embedding;
   3. Language model
   4. Similarity measure

10. Nature Language Process II

    1. Conditional probability and bayes theory
    2. Part-of-speech tagging

11. Nature Language Process III

    1. Multi-class classification
    2. IOB tagging
    3. Name Entity Recognition
    4. Document classification