Class activities will be recorded here.

This page is the one key spot to look to see what we have already done, what is planned for the current week, and what is planned for the remainder of the semester. Since the lectures are almost entirely buid around Jupyter Notebooks you will see links to these notebooks. These can be easily opened with and one extra mouse click if you setup your browser to associate `ipynb` files with Google Colab. Here is a short video where I demonstrate doing this in Chrome.

My setup example video

The approach is similar in other browsers. The punchliine of the video is you need a Google ID that you setup once to access Google Colaboratory and from then on links to ipynb files will just work.

Week 1 : January 17 - January 23

• Tuesday

  Introduction
  Brief course introduction and a quick review of Python in the context of Jupyter
  Notebook - module01_01_intro.ipynb

  Thursday

  Python Basics
  One language dominates modern ML - Python. This lecture is a whirl wind review
  Notebook - module00_01_python_intro.ipynb

Week 2 : January 24 - January 30

• Tuesday

  Labeled Data
  Loading common datasets and understanding the relationship between features and labels
  Notebook - module01_02_labeled_data.ipynb

  Thursday

  Introduction to Numpy
  Numpy is the backbone of much ML programming
  Notebook - module01_03_numpy.ipynb

Week 3 : January 31 - February 6

• Tuesday

  Vectors and Dot Products
  Practical motivation from images to motivate basics of understanding vectors/points
  Notebook - module01_04_vectors_dot_products.ipynb

  Thursday

  MatPlotLib
  Introduction to visualizing data through plots and histograms using MatPlotLib
  Noteobok - module01_05_matplotlib.ipynb

Week 4 : February 7 - February 13

• Tuesday

  MatPlotLib Continued
  More plotting with random variables and dataset creation thrown in

  Thursday

  Lines, Planes and Hyperplanes
  Linear decision boundaries expressed as lines, planes and hyperplanes
  Notebook - module02_01_hyperplanes.ipynb

Week 5 : February 14 - February 20

• Tuesday

  Matrices and then Perceptrons
  Quick review of matrices and then explanation of the Perceptron
  Notebook - module02_02_matrices.ipynb
  Notebook - module02_03_perceptron.ipynb

  Thursday

  Nearest Neighbor Classifiers
  Nearest Neighbor Classifer basics and a start at understanding generalization
  Notebook - module02_04_nearest_neighbors.ipynb

Week 6 : February 21 - February 27

• Tuesday

  More Nearest Neighbors
  Continued explanation of Nearest Neighbor Classifiers with regression example
  Notebook - module02_05_more_nearest_neighbors.ipynb

  Thursday

  Larger Neighborhoods using kNN
  Extending Nearest Neighbor to include multiple hits using k Neighbors

Week 7 : February 28 - March 6

• Tuesday

  Introduction to Linear Regression
  Fitting a parametric model to sample data to capture structure and make predictions
  Notebook - module03_01_linear_regression.ipynb

  Thursday

  Derivatives, Least-Squares and Outliers
  Using linear regression to motivate cover basics of least-squares optimization and outlier detection
  Notebook - module03_02_derivatives_regression_outliers.ipynb

Week 8 : March 7 - March 13

• Tuesday

  Multivariate Linear Regression
  Predicting a value from a vector using a linear function with learned parameters
  Notebook - module03_03_multivariate_linear_regression.ipynb

  Thursday

  Linear Regression with Gradient Descent
  Multivariate linear regression is an excellent opportunity to develop deeper insights into gradient descent
  Notebook - module03_04_linear_regression_gradient_descent.ipynb

Week 9 : March 14 - March 20

• Tuesday

  Polynomial Regression and Overfitting
  Transform a non-linear problem into a linear problem using polynomial combinations of features
  Notebook - module04_01_polynomial_basis_regression.ipynb

  Thursday

  Overfitting and Regularization
  In the context of polynomial regression illustrate risk of overfitting and also how regularization can help
  Notebook - module04_02_regularization.ipynb

Week 10 : March 21 - March 27

• Tuesday

  Cross-validation and Measuring Performance
  Cross validatio and stratification including visualizations then ways to measure accuracy
  Notebook - module05_01_cross_validation.ipynb
  Notebook - module05_02_classifier_accuracy.ipynb

  Thursday

  Decision Trees
  Classifers that work like a game of twenty questions
  Notebook - module06_01_decision_trees.ipynb

Week 11 : March 28 - April 3

• Tuesday

  Ensemble methods
  Combining the opinions of many classifiers - each in its own way flawed - can tap into wisdom of the crowd
  Notebook - module06_02_ensemble_methods.ipynb

  Thursday

  Probability
  A very quick review of probability pointing toward understanding better how randomness can both help and hurt
  Notebook - module07_01_probability.ipynb

Week 12 : April 4 - April 10

• Tuesday

  Introduction to Neural Networks
  Starting simply and building up the essential elements of a neural network
  Notebook - module08_01_neural_networks_mlp.ipynb

  Thursday

  Introducion to NN Continued
  Continued introduction to NNs and also introduced Assigment 4

Week 13 : April 11 - April 17

• Tuesday

  Spring Break

  Thursday

  Spring Break

Week 14 : April 18 - April 24

• Tuesday

  Neural Networks Using Keras
  Modern ML APIs such as Keras are fantastically useful but also require a degree of commitment to learn API idioms
  Notebook - module08_02_neural_networks_keras.ipynb

  Thursday

  Training a Network
  Examples of how to fit (train) networks emphasizing expressive power of hidden layers and convergence issues
  Same notebook as previous lecture

Week 15 : April 25 - May 1

• Tuesday

  Networks and Digit Recognition
  Using the MNIST dataset to construct neural networks suitable for hand written digit recognition
  Notebook - module09_01_neural_networks_mnist.ipynb

  Thursday

  Convolutional Neural Networks
  Using the CIFAR10 dataset to motivate and illustrate convolutional neural networks
  Notebook - module09_02_cnns_cifar10.ipynb

Week 16 : May 2 - May 8

• Tuesday

  CNNs continued and reflections on AI and ML
  Continue with explanation of CNNs and then a few thoughts about AI and ML

  Thursday

  Course Wrapup
  Student led question and answer about topics covered this semester
  42 Things you now now about ML