Lectures

You can download the lectures here. We will try to upload lectures prior to their corresponding classes. Future lectures listed below likely have broken links.

• 

  MSDS Student Orientation Session
  tl;dr: The first class will an orientation for the incoming MSDS students.
  
  
• 

  01 - Course Overview and Git
  tl;dr: We'll give an overview of the course and a quick tour of Git.
  [C1 Recording]
  

  Suggested Readings and Slides:

  • Course Overview
  • Git Slides
• 

  02 - Intro to Pandas and SciKit-Learn
  tl;dr: We'll do a brief introduction to Git, Pandas and Scikit-Learn which we will be using extensively in this course.
  [C1 Recording]
  

  Suggested Readings and Slides:

  • Pandas Slides
  • Scikit-Learn Slides
• 

  03 - A1 Spark Project Pitch Day
  tl;dr: The Spark team will introduce the projects for this semester and what the selection process is.
  
  

  Suggested Reading:

  • Section A1 pitch slides
• 

  03 - C1 Spark Project Pitch Day
  tl;dr: The Spark team will introduce the projects for this semester and what the selection process is.
  [C1 Recording]
  
• 

  04 - Probability and Linear Algebra Refresher
  tl;dr: We'll review some of the important concepts in probability and linear algebra which we will then apply in later lectures.
  [C1 Recording]
  

  Suggested Readings:

  • Probability Slides
  • Linear Algebra Slides
• 

  05 - Distance, Similarity Functions, and Time Series
  tl;dr: We'll review the concepts of distance, (dis)similarity functions, and time series.
  [C1 Recording]
  

  Suggested Readings:

  • Distances and Time Series
• 

  06 - Clustering I: k-Means
  tl;dr: We'll introduce our first unsupervised learning method, clustering with k-means.
  [C1 Recording]
  

  Suggested Readings:

  • k-means clustering
• 

  07 - Clustering II: In Practice
  tl;dr: We'll discuss practical aspects of clustering using k-means.
  [A1 Recording] [C1 Recording]
  

  Suggested Readings:

  • Clustering in Practice
• 

  08 - Clustering III: Hierarchical Clustering
  tl;dr: Description here.
  [A1 Recording] [C1 Recording]
  

  Suggested Readings:

  • Hierarchical Clustering
• 

  09 - Clustering IV: GMM and Expectation Maximization
  tl;dr: Description here.
  [A1 Recording] [C1 Recording]
  

  Suggested Readings:

  • GMM Slides
• 

  10 - Classification: Decision Trees and RandomForests
  tl;dr: Description here.
  [A1 Recording] [C1 Recording]
  

  Suggested Readings:

  • Decision Trees and Random Forests
• 

  11 - Classification - k-Nearest-Neighbors
  tl;dr: Description here.
  [A1 Recording] [C1 Recording]
  

  Suggested Readings:

  • Classification – kNN
• 

  12 - Classification: Naive Bayes and Support Vector Machines
  tl;dr: We will discuss the Naive Bayes and SVM classifiers.
  [C1 Recording TBD]
  

  Suggested Readings:

  • Naive Bayes and SVM
• 

  13 - SVD Low Rank Approximations
  tl;dr: We cover how the SVD can be used to compute low rank approximations to your data.
  [A1 Recording] [C1 Recording]
  

  Suggested Readings:

  • SVD – Low Rank Approximation
• 

  14 -- Dimensionality Reduction - PCA and tSNE
  tl;dr: We cover how to perform dimensionality reduction with PCA and tSNE.
  [A1 Recording] [C1 Recording]
  

  Suggested Readings:

  • Dimensionality Reduction and PCA
• 

  15 -- Linear Regression
  tl;dr: We explore linear regression and the methods for assessing your regression model.
  [A1 Recording] [C1 Recording]
  

  Suggested Readings:

  • Linear Regression
• 

  16 -- Logistic Regression and Regularization
  tl;dr: We explore logistic regression for binary classification and regularization for regression.
  [A1 Recording] [C1 Recording]
  

  Suggested Readings:

  • Logistic Regression
  • Regularization
• 

  18 -- Neural Networks I
  tl;dr: The focus of this lecture is on gradient descent.
  [A1 Recording] [C1 Recording]
  

  Suggested Readings:

  • Neural Networks I
• 

  19 -- Neural Networks II
  tl;dr: This lecture introduces neural networks, the computational graph, and back propagation.
  [A1 Recording] [C1 Recording]
  

  Suggested Readings:

  • Neural Networks II
• 

  20 -- Neural Networks III
  tl;dr: This lecture introduces convolutional neural networks (CNNs).
  [A1 Recording] [C1 Recording]
  

  Suggested Readings:

  • Neural Networks III
• 

  21 -- Recommender Systems
  tl;dr: We'll cover the basics of recommender systems, including collaborative filtering, matrix facotorization and deep learning approaches.
  [A1 Recording] [C1 Recording]
  

  Suggested Readings:

  • Recommender Systems – Course Notes
• 

  22 -- Networks I
  tl;dr: We introduce graph theory for representing networks.
  [A1 Recording] [C1 Recording]
  

  Suggested Readings:

  • Networks I
• 

  23 -- Networks 2
  tl;dr: We discuss centrality measures for graphs.
  [A1 Recording] [C1 Recording]
  

  Suggested Readings:

  • Networks II
• 

  24 -- Time Series Analysis
  tl;dr: We'll cover the basics of time series analysis, including visualizing, modeling, and forecasting.
  [A1 Recording] [C1 Recording]
  

  Suggested Readings:

  • Time Series Analysis – Course Notes
• 

  25 -- RNNs
  tl;dr: We introduce the Recurrent Neural Network architecture.
  [A1 Recording] [C1 Recording]
  

  Suggested Readings:

  • Recurrent Neural Networks – Course Notes
• 

  26 -- NLP I
  tl;dr: Historical perspective on NLP and modern machine learning techniques.
  [A1 Recording] [C1 Recording]
  

  Suggested Readings:

  • Natural Language Processing – Course Notes
• 

  26 -- NLP II
  tl;dr: We present a Jupyter notebook illustrating how to fine-tune a Sequence to Sequence model.
  [A1 Recording] [C1 Recording]
  

  Suggested Readings:

• 

  Final Project Presentations -- Part 1
  tl;dr: Description here.
  
  

  Presentation order TBD.

• 

  Final Project Presentations
  tl;dr: Description here.
  
  

  Presentation order TBD.

• 

  Final Project Presentations -- Part 2
  tl;dr: Description here.
  
  

  Presentation order TBD.