Practical Artificial Intelligence Programming
Explore the dynamic field of generative artificial intelligence in our Practical Artificial Intelligence Programming course, which emphasizes modern AI methodologies through a learning-by-doing approach. This course is designed to equip students with a thorough understanding of both the theoretical foundations and practical implementations of cutting-edge AI technologies. It spans a wide array of topics, including core AI principles, industry best practices, and the deployment of AI systems in real-world scenarios. The curriculum culminates in a final project, where students apply their skills to a research initiative or a practical application. This project not only challenges students to tackle specific problems but also allows them to explore specialized interests, showcasing their capability to develop innovative and effective AI solutions.
Basics and Preliminaries
- Sept 20
- Lecture 1
Introduction: The Road to Deep Learning- HW 1 OUT
- Sept 27
- Lecture 2
Preliminaries: Linear Algebra - Oct 11
- Lecture 3
Preliminaries: Probability- HW 2 OUT
- Oct 18
- Lecture 4
Regression: Linear Neural Networks- HW 1 DUE
- Oct 25
- Lecture 5
Regression: Object-Oriented Design - Nov 1
- Lecture 6
Classification: Image Dataset & Softmax Regression- HW 3 OUT
- Nov 8
- Lecture 7
Classification: Generalization- HW 2 DUE
Deep Learning Techniques
- Nov 15
- Lecture 8
MLP: Building Blocks & Computational Graphs - Nov 22
- Lecture 9
MLP: Overfitting & Regularization- HW 4 OUT
- Nov 29
- Lecture 10
MLP: Layers, Modules and Parameters- HW 3 DUE
- Project Proposal DUE
- HW 3 DUE
- Dec 6
- Lecture 11
ConvNets: Convolution & Normalization - Dec 13
- Lecture 12
ConvNets: LeNet, AlexNet and VGGNet - Dec 20
- Lecture 13
ConvNets: ResNet, ResNeXt and DenseNet- HW 4 DUE
Final Projects
- Dec 27
- Lecture 14
Final Projects: Presentation - Jan 3
- Lecture 15
Final Projects: Presentation - Jan 10
- Project Report DUE