This course provides a basic introduction to the machine learning pipeline and related concepts. Topics covered include: Machine learning uses and applications; data set requirements; data pre-processing; data annotation, and validation; data representation formats; features and feature representation and extraction; the vector space model; traditional machine learning algorithms; machine learning algorithms and programming; ML evaluation methods; introduction to deep learning algorithms; big data; reinforcement learning; Unsupervised learning; statistical significance analysis; and other special topics.
Tue and Thu 6-8 pm
Ricardo A. Calix, Ph.D.
Purdue University Northwest
rcalix@pnw.edu
241 Anderson
Thursday 2-4 pm (or by appointment)
Brightspace
Environment:
AWS
WL Scholar
Labs
We will use the following software:
Sun | Mon | Tue | Wed | Thu | Fri | Sat |
---|---|---|---|---|---|---|
Jan 7 |
Jan 8 Introduction |
Jan 9 |
Jan 10 Defining ML problems |
Jan 11 |
Jan 12 | Jan 13 |
Jan 14 | Jan 15 | Jan 16 |
Jan 17 Matrices, vectors with Numpy |
Jan 18
Lab: |
Jan 19 | Jan 20 |
Jan 21 |
Jan 22 WEKA |
Jan 23 |
Jan 24 WEKA |
Jan 25 |
Jan 26 | Jan 27 |
Jan 28 |
Jan 29 KNNPipeline code and the Accuracy metric with numpy Performance Metrics lecture |
Jan 30 |
Jan 31 Linking performance metrics with KNN using python, read IRIS csv |
Feb 1 |
Feb 2 | Feb 3 |
Feb 4 |
Feb 5 Deep Learning with Tensorflow.js and KerasDeploying to the web |
Feb 6 |
Feb 7 The Classic XOR problem |
Feb 8 |
Feb 9 | Feb 10 |
Feb 11 |
Feb 12 Exam 1 |
Feb 13 |
Feb 14 The Classic XOR problem |
Feb 15 |
Feb 16 | Feb 17 |
Feb 18 |
Feb 19 Neural networks intuition and a bit of history |
Feb 20 |
Feb 21 Work on HW |
Feb 22 |
Feb 23 | Feb 24 |
Feb 25 |
Feb 26 The Perceptron |
Feb 27 |
feb 28 The Perceptron |
Feb 29 |
Mar 1 | Mar 2 |
Mar 3 |
Mar 4 CIFAR-10, DNNs, and CNNs |
Mar 5 |
Mar 6 CIFAR-10, DNNs, and CNNs |
Mar 7 |
Mar 8 | Mar 9 |
Mar 10 | Mar 11 | Mar 12 | Mar 13 | Mar 14 | Mar 15 | Mar 16 |
Mar 17 |
Mar 18 Exam 2 |
Mar 19 |
Mar 20 Intuition of loss functions |
Mar 21 |
Mar 22 | Mar 23 |
Mar 24 |
Mar 25 |
Mar 26 |
Mar 27 |
Mar 28 |
Mar 29 | Mar 30 |
Mar 31 |
Apr 1 |
Apr 2 |
Apr 3 Multi-Layer Perceptron |
Apr 4 |
Apr 5 | Apr 6 |
Apr 7 |
Apr 8 Naive Bayes algorithm in numpyHMM |
Apr 9 |
Apr 10 Reinforcement Learning |
Apr 11 |
Apr 12 | Apr 13 |
Apr 14 |
Apr 15 Singular Value Decomposition and Recommender Systems |
Apr 16 |
Apr 17 Singular Value Decomposition and Recommender Systems How to use SVD and distance metrics to recommend movies |
Apr 18 |
Apr 19 | Apr 20 |
Apr 21 | Apr 22 Project Presentations |
Apr 23 |
Apr 24
|
Apr 25 | Apr 26 | Apr 27 |
Apr 28 | Apr 29 Finals |
Apr 30 Finals |
May 1 Finals |
May 2 Finals |
May 3 Finals |
May 4 |