CPTS 434/534 – Neural Network Design and Application

Course Overview

CPTS 434/534 introduces the foundations and practical aspects of deep neural networks, a cornerstone of modern machine learning. The course blends theoretical concepts in statistical learning with hands-on implementation of key deep learning models.

Learning Outcomes:

  • Principles of representation learning and optimization
  • Implementation of a variety of neural network architectures (MLPs, CNNs, RNNs, transformers, etc.)
  • Practical training techniques and modern neural network variants

By the end of the course, students will understand how deep models are designed, trained, and applied to real-world data across vision, sequence and structured data domains.

Syllabus and Schedule

Lecture Schedule

Lecture Topic Slides
1 [0] Syllabus and Overview  
2 [ML] ML Basics Slides
3 [ML] PAC Learning Slides
4 [ML] ERM and MLE Slides
5 [TA] HW1 and Coding Tools Slides
6 [NN] NN Basics Slides
7 [NN] Compositing Units in NN Slides
8 [NN] MLP Softmax Classifier Slides
9 [CNN] Convolutional Layer and CNN Slides
10 [CNN] CNN Architectures Slides
11 [CNN] Practical Training of CNN Slides
12 [RNN] Sequence Data and RNN Slides
13 [RNN] LSTM and RNN Architectures Slides
14 [ModernNN] Attention Mechanism  
15 [ModernNN] Transformer and ViT  
16 [GNN] Graph Data and Representation  
17 [GNN] GNN  
18 [GenAI] GAN and VAE  
19 [GenAI] Diffusion Models  
20 [FM] Foundation Models  
21 [FM] Multimodal Foundation Models  
22 [FL] Federated Learning  
23 [UQ] Conformal Prediction and Mean-Risk Model  
24 [Agent] Agentic Workflow  

Assignment Materials

Assignments Topic/Section Materials
HW1 ML Start Code, HW Note
HW2 NN Start Code
HW3 CNN Start Code
HW4 Transformer + ViT  
HW5 RNN + GNN  
HW6 GenAI