====== Schedule ====== ---- Video of the lectures is available via the echo360 portal of the course. A link will be provided on Canvas. |< 100% 18% 40% 19% 13% >| | ^ Topics ^ Reading ^ Assignments ^ ^ Week 1: August 20-24 | | | | | Monday | Course introduction ({{wiki:01_intro.pdf | slides}}). | Sections 1.1 and 1.2 in the textbook | | | Wednesday | Course introduction (continued). | Sections 1.1 and 1.2 in the textbook | | | Friday | Course introduction and [[http://jupyter.org/| Jupyter]] notebooks. | | [[http://nbviewer.ipython.org/url/www.cs.colostate.edu/~cs545/fall18/notebooks/assignment1.ipynb | Assignment 1]] is available. **Due 9/7**. | ^ Week 2: August 27-31 | | | | | Monday | Overview of Numpy ([[http://nbviewer.ipython.org/url/www.cs.colostate.edu/~cs545/fall18/notebooks/01_numpy.ipynb | notebook]]) and Matplotlib ([[http://nbviewer.ipython.org/url/www.cs.colostate.edu/~cs545/fall18/notebooks/01_matplotlib.ipynb | notebook]]). | A [[https://www.labri.fr/perso/nrougier/from-python-to-numpy/| tutorial ]] on how to write efficient code using Numpy | | | Wednesday | Linear models and the perceptron algorithm ({{wiki:02_linear.pdf | slides}}). | Chapter 1, and Section 3.1 in the textbook | | | Friday | Linear models (continued). Perceptron [[http://nbviewer.ipython.org/url/www.cs.colostate.edu/~cs545/fall18/notebooks/02_perceptron.ipynb | notebook]]. | | | ^ Week 3: September 4-7 | | | | | Wednesday | Linear regression ({{wiki:03_linear_regression.pdf | slides}}). | Chapter 3.2 | | | Friday | Linear regression (continued). | Chapter 3.2 | [[http://nbviewer.ipython.org/url/www.cs.colostate.edu/~cs545/fall18/notebooks/assignment2.ipynb | Assignment 2]] is available. **Due 9/21** | ^ Week 4: September 10-14 | | | | | Monday | Logistic regression ({{wiki:04_logistic_regression.pdf | slides}}). | Chapter 3.3 | | | Wednesday | Logistic regression (continued). | Chapter 3.3 | | | Friday | Overfitting ({{wiki:05_overfitting.pdf | slides}}). | Chapter 2.3,4.1 | | ^ Week 5: September 17-21 | | | | | Monday | Overfitting (continued). Regularization ({{wiki:06_regularization.pdf | slides}}). | Chapter 4 | | | Wednesday | Regularization (continued). Classifier weights as a function of the regularization parameter ([[http://nbviewer.ipython.org/url/www.cs.colostate.edu/~cs545/fall18/notebooks/03_ridge_coeffs.ipynb | notebook]]) | Chapter 4 | | | Friday | Cross validation ([[http://nbviewer.ipython.org/url/www.cs.colostate.edu/~cs545/fall18/notebooks/04_cross_validation.ipynb | notebook]]). | | [[http://nbviewer.ipython.org/url/www.cs.colostate.edu/~cs545/fall18/notebooks/assignment3.ipynb | Assignment 3]] is available. **Due 10/5**. | ^ Week 6: September 24-28 | | | | | Monday | Measuring classifier accuracy/error ({{wiki:07_classifier_accuracy.pdf | slides}}). [[http://nbviewer.ipython.org/url/www.cs.colostate.edu/~cs545/fall18/notebooks/05_classifier_accuracy.ipynb | Notebook on classifier accuracy/error]]. | | | | Wednesday | Support vector machines ({{wiki:08_svm.pdf | slides}}). Useful resource: {{http://www.cs.colostate.edu/~asa/pdfs/howto.pdf|A user's guide to support vector machines}}. | Chapter e-8 | | | Friday | Support vector machines (continued). | Chapter e-8 | | ^ Week 7: October 1-5 | | | | | Monday | A deeper look at SVMs ({{wiki:09_svm_loss_unbalanced.pdf | slides}}). Code for the [[code:demo2d|svm demo]]. | | | | Wednesday | Nonlinear SVMs: kernels ({{wiki:10_kernels.pdf | slides}}). | Chapter e-8 | | | Friday | Kernels (continued). | Chapter e-8 | [[http://nbviewer.ipython.org/url/www.cs.colostate.edu/~cs545/fall18/notebooks/assignment4.ipynb | Assignment 4]] is available. **Due 10/19**. | ^ Week 8: October 8-12 | | | | | Monday | Classifier evaluation ({{wiki:11_evaluation.pdf | slides}}). | | | | Wednesday | Model selection in scikit-learn [[http://nbviewer.ipython.org/url/www.cs.colostate.edu/~cs545/fall18/notebooks/06_model_selection.ipynb | notebook]]. | | | | Friday | Kernels (continued). | | | ^ Week 9: October 15-19 | | | | | Monday | Neural networks ({{wiki:12_nn.pdf | slides}}). [[http://nbviewer.ipython.org/url/www.cs.colostate.edu/~cs545/fall18/notebooks/07_neural_networks.ipynb | notebook]]. | Chapter e-7 | | | Wednesday | Neural networks (continued). | Chapter e-7 | | | Friday | Neural networks (continued). | Chapter e-7 | Project proposals due Nov 3rd. | ^ Week 10: October 22-26 | | | | | Monday | Neural networks (continued). | Chapter e-7 | [[http://nbviewer.ipython.org/url/www.cs.colostate.edu/~cs545/fall18/notebooks/assignment5.ipynb | Assignment 5]] is available. **Due 11/6** | | Wednesday | Neural networks (continued) (updated {{wiki:12_nn.pdf | slides}}). | Chapter e-7 | | | Friday | Deep networks ({{wiki:13_deep_networks.pdf | slides}}). | Chapter e-7 | | ^ Week 11: October 29 - November 2 | | | | | Monday | PyTorch. [[http://nbviewer.ipython.org/url/www.cs.colostate.edu/~cs545/fall18/notebooks/08_pytorch_tensors.ipynb | tensors]] and [[http://nbviewer.ipython.org/url/www.cs.colostate.edu/~cs545/fall18/notebooks/09_pytorch_nn.ipynb | neural networks]] | Also see the [[https://pytorch.org/tutorials/|PyTorch tutorials]]. | | | Wednesday | Convolutional networks. | | | Friday | Convolutional networks in PyTorch. [[http://nbviewer.ipython.org/url/www.cs.colostate.edu/~cs545/fall18/notebooks/10_pytorch_convnet.ipynb | notebook]]. | | ^ Week 12: November 4 - 9 | | | | | Monday | Deep learning: auto-encoders ({{wiki:13_deep_networks.pdf | slides}}). Multi-class classification ({{wiki:14_multi_class.pdf | slides}}); a [[code:multi_class| demo]] of multi-class classification | Chapter e-7 | | Wednesday | Features: selection and scaling ({{wiki:15_feature_selection.pdf | slides}}) | Chapter e-9 | | Friday | Feature selection (continued) [[http://nbviewer.ipython.org/url/www.cs.colostate.edu/~cs545/fall18/notebooks/11_feature_selection.ipynb | notebook]] | Chapter e-9 | ^ Week 13: November 11 - 16 | | | | | Monday | Principal component analysis (PCA) ({{wiki:16_pca.pdf | slides}}). [[http://nbviewer.ipython.org/url/www.cs.colostate.edu/~cs545/fall18/notebooks/12_pca.ipynb | notebook]] | Chapter e-9 | | Wednesday | Nearest neighbor classification ({{wiki:17_nearest_neighbors.pdf | slides}}). | Chapter e-9 | | Friday | Nearest neighbor classification [[http://nbviewer.ipython.org/url/www.cs.colostate.edu/~cs545/fall18/notebooks/13_nearest_neighbors.ipynb | notebook]] . | Chapter e-9 | ^ Thanksgiving week | | | | ^ Week 14: November 26 - 30 | | | | | Monday | Discussion of final report. | | Final report due Wednesday Dec 12th | | Wednesday | Clustering ({{wiki:18_clustering.pdf | slides}}). [[http://nbviewer.ipython.org/url/www.cs.colostate.edu/~cs545/fall18/notebooks/14_kmeans.ipynb | notebook]] | Chapter 10 in [[http://www-bcf.usc.edu/~gareth/ISL/|introduction to statistical learning]] | | | Friday | Clustering (continued). | Chapter 10 in [[http://www-bcf.usc.edu/~gareth/ISL/|introduction to statistical learning]] | | ^ Week 15: December 3 - 7 | | | | | Monday | Ensemble methods ({{wiki:19_ensembles.pdf | slides}}). [[http://nbviewer.ipython.org/url/www.cs.colostate.edu/~cs545/fall18/notebooks/15_ensemble.ipynb | notebook]] | | | | Wednesday | Course summary ({{wiki:20_course_summary.pdf | slides}}). [[http://nbviewer.ipython.org/url/www.cs.colostate.edu/~cs545/fall18/notebooks/15_ensemble.ipynb | notebook]] | | | | Friday | Poster session | | | ^ Week 16 | | | | | Wednesday | Submit final reports | | |