Weekly Schedule

The schedule along with the list of topics to be covered are tentative and subject to change.

Week		Date	Module	Topic	Assignment
1	T	1/20	Introduction	Welcome and course overview	Post a note on Teams to introduce yourself. Review the Syllabus.
	R	1/22		Linear algebra basics; Numpy and PyTorch basics	Setup software and development environment for the course (see here)
2	T	1/27	Linear Neural Networks for Regression	Linear regression
	R	1/29		Linear regression
3	T	2/3		Linear regression implementation from scratch and with PyTorch
	R	2/5		Generalization, overfitting, and regularization
4	T	2/10	Linear Neural Networks for Classification	Logistic regression
	R	2/12		Softmax regression
5	T	2/17		Softmax regression implementation from scratch
	R	2/19		Softmax regression implementation with PyTorch; Classifier generalization
6	T	2/24	Non-linear Neural Networks	Multi-layer perceptrons
	R	2/26		Multi-layer perceptron implementation from scratch and with PyTorch
7	T	3/3		Computational graphs and backpropagation; Network initialization
	R	3/5	Convolutional Neural Networks (CNNs)	Introduction
8	T	3/10		CNN details
	R	3/12		Mid-term Exam in Wagar 133
9	T	3/17		No class: Spring recess
	R	3/19		No class: Spring recess
10	T	3/24		The LeNet CNN
	R	3/26	Modern CNNs	AlexNet and VGGs
11	T	3/31		ResNet; Batch Normalization; Dropout
	R	4/2	Recurrent Neural Networks	Introduction
12	T	4/7		LSTMs for text classification
	R	4/9	Transformers	The attention mechanism
13	T	4/14		Transformer architecture; Transformers for text classification
	R	4/16		Large language models (LLMs)
14	T	4/21	Reinforcement Learning (RL)	Introduction
	R	4/23		RL with neural networks
15	T	4/28		Applying RL to control a robot
	R	4/30	Additional Topics	Optimization algorithms
16	T	5/5		What did we miss?
	R	5/7		Can we trust AI?
17	T	5/12		Final Exam in Wagar 133 (9:40-11:40 am)