Interactive course — Advanced Computer Science

Machine Learning

Advanced quantitative techniques to analyze data where humans fall short.

Back

Overview

Machine learning swoops in where humans fail — such as when there are hundreds (or hundreds of thousands) variables to keep track of and millions (or billions, or trillions) of pieces of data to process.

This course develops the mathematical basis needed to deeply understand how problems of classification and estimation work. By the end of this course, you’ll develop the techniques needed to analyze data and apply these techniques to real-world problems.

Topics covered

  • Bagging and Boosting
  • Classification
  • K-nearest Neighbors
  • Kernels
  • Linear Regression
  • Logistic Regression
  • Naive Bayes
  • Optimization
  • Supervised Learning
  • Support Vector Machine
  • Trees
  • Unsupervised Learning

Interactive quizzes

26

Concepts and exercises

210+

Course map

Prerequisites and Next Steps

  1. 1

    Linear Regression

    Get your basics in line.

    1. Introduction to Linear Regression

      The basics of prediction with a very simple model: a line.

      1
    2. Statistics of Linear Regression

      Dive into the math behind linear regression.

      2
    3. Linear Algebra in Linear Regression

      Brush up on linear algebra, a key tool throughout machine learning.

      3
    4. Higher Dimensional Regression

      What happens when you need to do a regression with more than two variables? Hyperplanes!

      4
    5. Limitations of Linear Regression

      When variables are related non-linearly, linear regression falls short.

      5
    6. Alternatives to Linear Regression

      Get familiar with ridge regression, lasso, nearest neighbors, and other approaches.

      6
  2. 2

    Linear Classification

    Classifying both quantitative and qualitative data.

    1. Indicator Matrix

      Add this clever relationship representation to your tool kit.

      7
    2. Logistic Classification

      Instead of giving a definitive 'yes' or 'no', this method predicts probabilities of 'yes' or 'no'.

      8
    3. Linear Discriminant Analysis

      Explore this powerful tool for separating classes of normally distributed data.

      9
    4. KNN Classification

      "My neighbors are my friends", as a classification algorithm.

      10
    5. Perceptrons

      The judge and jury for classification.

      11
    6. Naive Bayes

      Bayes' theorem - a classic tool of probability - guides this classication method.

      12
  3. 3

    Trees

    Explore this versatile model and related ideas like bagging, random forests, and boosting.

    1. Tree Regression

      A versatile tool, best applied when there are strong distinctions between cases.

      13
    2. Tree Classification

      The basics of classification via a tree.

      14
    3. Trees: Pros, Cons, and Best Practices

      A major advantage of trees is their interpretability. What are the drawbacks?

      15
    4. Bagging

      Reduce the model variance by averaging across many trees!

      16
    5. Boosting

      "Teammates who complement each other's weaknesses", trees edition.

      17
  4. 4

    Support Vector Machine

    Divide classes with the best possible margin of error.

    1. Hard Margin Support Vector Machines

      The wall of SVMs: you're either in or you're out.

      18
    2. Soft Margin Support Vector Machines

      Explore this SVM that works even when some points end up on the "wrong side of the wall".

      19
    3. Nonlinear Decision Boundaries

      Sometimes, the best wall isn't a straight line.

      20
    4. More than Two Classes

      Learn how to combine several classifiers to handle data sets with many classes.

      21
    5. Connection to Logistic Regression

      SVMs are similar to logistic regression - but not exactly the same! Find out why.

      22
  5. 5

    Kernels

    It's time to upgrade the dot product.

    1. Intro To Kernels

      Get down the basics of this tool which helps measure the similarity of vectors.

      23
    2. Kernel Boundaries

      Use kernels to classify new data by comparing it to existing data.

      24
    3. Kernel Support Vector Machines

      See why SVMs are one of the best models for employing kernels.

      25
    4. Using the Kernel Trick

      Explore the power of the kernel trick, and the drawbacks and pitfalls of using kernels.

      26