Schedule

Schedule#

The course schedule is updated regularly. Please check it frequently for the latest information.

C. Fanelli office hours: Friday, 9:30-11:30, office ISC-1265
J. Giroux (TA) office hours: Friday, 11:30-1:30, office ISC-1109

Last update: (4/17/2025)

Week 1 (Mon, Jan 20 - Sun, Jan 26)#

Time	Tuesday	Thursday	Friday
9:30am-11:30am			Office hours (C. Fanelli, Prof)
11:30am-1:30pm			Office hours (J. Giroux, TA)
2:00pm-3:20pm	No class	Lecture: Course Introduction and History of Deep Learning What to learn: Understand course schedule and how you will be graded

Readings for week 1 and week 2: Based on Raschka, Chap. 2 + notes in class

Week 2 (Mon, Jan 27 - Sun, Feb 2)#

Time	Tuesday	Thursday	Friday
9:30am-11:30am			Office hours (C. Fanelli, Prof)
11:30am-1:30pm			Office hours (J. Giroux, TA)
2:00pm-3:20pm	Lecture: Implementing a perceptron learning algorithm in Python What to learn: Training a perceptron model	Lecture: Machine Learning classifier for supervised learning What to learn: Logistic regression, loss function, intro to overfitting and ways to tackle it What to submit (due Feb 2): (Bonus) Assignment 0 - example activity on HPC

Assignment 0 (assigned Jan 28; due Jan 31)

Readings for week 1 and week 2: Based on Raschka, Chap. 2 + notes in class

Week 3 (Mon, Feb 3 - Sun, Feb 9)#

Time	Tuesday	Thursday	Friday
9:30am-11:30am			Office hours (C. Fanelli, Prof)
11:30am-1:30pm			Office hours (J. Giroux, TA)
2:00pm-3:20pm	Lecture: Data Preprocessing What to learn: Building good training datasets, dealing with missing data, handling categorical data, partitioning training/test datasets, assessing feature importance	Lecture: Regularization What to learn: regularization, problem complexity and feature importance

Readings for Feb 3 and Feb 5 Lectures: Raschka, Chap. 4

Week 4 (Mon, Feb 10 - Sun, Feb 16)#

Time	Tuesday	Thursday	Friday
9:30am-11:30am			Office hours (C. Fanelli, Prof)
11:30am-1:30pm			Office hours (J. Giroux, TA)
2:00pm-3:20pm	Lecture: Model Evaluation and Hyperparameter Tuning What to learn: Streamlining workflows, cross-validation, learning and validation curves, fine-tuning	Lecture: Developing a Multi-Layer Neural Network from Scratch What to learn: forward propagation, training via backpropagation, convergence

Assignment 1 (assigned Feb 16; due Feb 26)

Readings for Feb 11 Lecture: Main concepts from Raschka, Chap. 6

Readings for Feb 13 Lecture: Based on Raschka, Chap. 11

Week 5 (Mon, Feb 17 - Sun, Feb 23)#

Time	Tuesday	Thursday	Friday
9:30am-11:30am			Office hours (C. Fanelli, Prof)
11:30am-1:30pm			Office hours (J. Giroux, TA)
2:00pm-3:20pm	Lecture: Parallelizing a NN with PyTorch What to learn: Manipulating tensors, DataLoader, model training, optimization	No class today

Readings for Feb 18 and 20 Lectures: Based on Raschka, Chap. 12; Chap. 13 pages 410-412, 415-417, 417-430, 436-439

Week 6 (Mon, Feb 24 - Sun, Mar 2)#

Time	Tuesday	Thursday	Friday
9:30am-11:30am			Office hours (C. Fanelli, Prof)
11:30am-1:30pm			Office hours (J. Giroux, TA)
2:00pm-3:20pm	Lecture: Building a NN with PyTorch and PyTorch Computation Graphs What to learn: Transiotning from building a NN from scratch to leveraging built-in functionalities in PyTorch	Lecture: PyTorch Computation Graphs What to learn: Understanding computation graphs; creating a graph in PyTorch; computing gradients; understanding autodifferentiation. What to submit (…): Assignment 1 - Building a NN from Scratch (see past weeks)

Reminder Assignment 1 due Feb 28 (new date)

Readings for Feb 26 and 28 Lectures: Based on Raschka, Chap. 12; Chap. 13 pages 410-412, 415-417, 417-430, 436-439

Week 7 (Mon, Mar 3 - Sun, Mar 9)#

Time	Tuesday	Thursday	Friday
9:30am-11:30am			Office hours (C. Fanelli, Prof)
11:30am-1:30pm			Office hours (J. Giroux, TA)
2:00pm-3:20pm	Lecture: Convolutional Neural Networks What to learn: Understanding CNN and feature hierarchies, implementing a CNN	Lecture: Convolutional Neural Networks What to learn: Hands-on with classification problems

Assignment 2 (assigned Mar 8; due Mar 21)

Readings for Mar 4 and Mar 6 Lectures: Based on Raschka, Chap. 14

Week (Mon, Mar 10 - Sun, Mar 16)#

Time	Monday	Tuesday	Wednesday	Thursday	Friday
All day	Spring Break	Spring Break	Spring Break	Spring Break	Spring Break

Week 8 (Mon, Mar 17 - Sun, Mar 23)#

Time	Tuesday	Thursday	Friday
9:30am-11:30am			Office hours (C. Fanelli, Prof)
11:30am-1:30pm			Office hours (J. Giroux, TA)
2:00pm-3:20pm	Lecture: (Continue) CNN What to learn: CNN for classification and/or regression problems	Lecture: An Introduction to GradCAM for explainability of CNN What to learn: practical understanding of GradCAM, case studies and applications

Reminder Assignment 2 due Mar 21 (new date)

Week 9 (Mon, Mar 24 - Sun, Mar 30)#

Time	Tuesday	Thursday	Friday
9:30am-11:30am			Office hours (C. Fanelli, Prof)
11:30am-1:30pm			Office hours (J. Giroux, TA)
2:00pm-3:20pm	Lecture: Recurrent Neural Network What to learn: modeling sequential data using RNN	Lecture: Recurrent Neural Network What to learn: Building an RNN model

Readings for Mar 25 and Mar 27 Lectures: Raschka, Chap. 15

Week 10 (Mon, Mar 31 - Sun, Apr 6)#

Time	Tuesday	Thursday	Friday
9:30am-11:30am			Office hours (C. Fanelli, Prof)
11:30am-1:30pm			Office hours (J. Giroux, TA)
2:00pm-3:20pm	Lecture: RNN What to learn: hidden to hidden recurrence, full example with LSTM; integration of other approaches (GRU, etc)	Lecture: Generative Adversarial Networks What to learn: Implementing GAN from scratch; Training, implementing generator and discriminator networks

Readings: Raschka, Chap. 17

Week 11 (Mon, Apr 7 - Sun, Apr 13)#

Time	Tuesday	Thursday	Friday
9:30am-11:30am			Office hours (C. Fanelli, Prof)
11:30am-1:30pm			Office hours (J. Giroux, TA)
2:00pm-3:20pm	Lecture: Convolutional and Wasserstein GAN What to learn: WGAN, DCGAN	Lecture: WGAN

Assignment 3 (assigned Apr 10; due Apr 20)
Readings: Raschka, Chap. 17

Week 12 (Mon, Apr 14 - Sun, Apr 20)#

Time	Tuesday	Thursday	Friday
9:30am-11:30am			Office hours (C. Fanelli, Prof)
11:30am-1:30pm			Office hours (J. Giroux, TA)
2:00pm-3:20pm	Lecture: Complete lectures on GAN; Intro Graph Neural Networks What to learn: Undirected graphs, directed graphs, understanding graph convolutions	Lecture: Graph Neural Networks What to learn: Implementation of a GNN from scratch using Pytorch

Reminder Assignment 3 due Apr 20 (new date)
Assignment 4 (assigned Apr 21; due Apr 27)

Readings: Raschka, Chap. 18

Week 13 (Mon, Apr 21 - Sun, Apr 27)#

Time	Tuesday	Thursday	Friday
9:30am-11:30am			Office hours (C. Fanelli, Prof)
11:30am-1:30pm			Office hours (J. Giroux, TA)
2:00pm-3:20pm	Lecture: GNN	Lecture: GNN

Reminder Assignment 4 due Apr 27