Lectures

The lectures are available for download here. We will upload them ahead of the corresponding classes whenever possible. Given the broad and comprehensive topics in this course, we greatly value the shared external resources. We acknowledge and respect the copyrights of publicly available materials, including those from Stanford CS231n Spring 2024, Lil’Log, and other public resources as referenced and noted in the slides. If any oversight has occurred, please do not hesitate to contact Guangjing.

• 

  Trustworthy AI Systems Overview
  tl;dr: An overview of trustworthy AI system principles and course syllabus.
  [slides]
  

  Suggested Readings:

  • HHS Trustworthy AI Playbook
• 

  Deep Learning for Image Classification
  tl;dr: A review of deep learning basics and its application in image classifcation.
  [slides]
  

  Suggested Readings:

  • Deep Residual Learning for Image Recognition
  • A Survey of Convolutional Neural Networks
• 

  Deep Learning for Image Segmentation
  tl;dr: An introduction to semantic segmentation, object detection and instance segmentation.
  [slides]
  

  Suggested Readings:

  • Ultralytics
  • Image Segmentation Using Deep Learning
• 

  Generative Modeling (Part I)
  tl;dr: An introduction to generative adversarial network and neural style transfer.
  [slides]
  

  Suggested Readings:

  • Generative Adversarial Nets
  • Generative Adversarial Networks in Computer Vision
• 

  Generative Modeling (Part II)
  tl;dr: An introduction to variational autoencoder and diffusion models.
  [slides]
  

  Suggested Readings:

  • Diffusion Models in Vision
  • Diffusion Model Blog
  • Variational Autoencoder Blog
• 

  Deep Learning for Audio Recognition
  tl;dr: An introduction to speech and speaker recognition and human factors in deepfake audio detection.
  [slides]
  

  Suggested Readings:

  • X-Vector
  • Audio Deepfake Detection
• 

  Deep Learning for Voice Conversion
  tl;dr: An introduction to voice conversion techniques and potential attacks.
  [slides]
  

  Suggested Readings:

  • VC Paper/Project List
• 

  Pretrained Foundation Models
  tl;dr: An introduction to the recurrent neural network, attention, transformers and foundation models.
  [slides]
  

  Suggested Readings:

  • Foundation Model Paper 1
  • Foundation Model Paper 2
  • Building Large Language Models
• 

  Large Language Model Agent
  tl;dr: An introduction to the large language model agents.
  [slides]
  

  Suggested Readings:

  • LLM Powered Autonomous Agents
  • Application Development using LLMs
• 

  Hallucinations in Large Language Models
  tl;dr: An introduction to LLM hallucination causes, detection and mitigation.
  [slides]
  

  Suggested Readings:

  • Extrinsic Hallucinations in LLMs
  • A Survey on Hallucination in LLMs
• 

  Security of AI in Inference
  tl;dr: An introduction to adversarial attacks and defenses.
  [slides]
  

  Suggested Readings:

  • Adversarial Example Papers
  • Adversarial Attacks on LLMs
• 

  Security of AI in Training
  tl;dr: An introduction to poisoning attacks and defenses.
  [slides]
  

  Suggested Readings:

  • Survey on Poisoning Attacks
  • Survey on Attack Transferability
• 

  Privacy of AI
  tl;dr: An introduction to privacy attacks and defenses.
  [slides]
  

  Suggested Readings:

  • Differential Privacy
  • Survey on ML and Privacy
• 

  Accountability of AI
  tl;dr: An introduction to accountability, AI-generated content detection and watermarking.
  [slides]
  

  Suggested Readings:

  • Text Watermarking
  • Evading Watermark based Detection of AI-Generated Content
• 

  Robustness of AI
  tl;dr: An introduction to uncertainty and robustness.
  [slides]
  

  Suggested Readings:

  • AI Robustness
  • Out-of-Distribution Robustness in Deep Learning
• 

  Explainability of AI
  tl;dr: An introduction to explainability methods.
  [slides]
  

  Suggested Readings:

  • Explainable AI Survey
  • Explainable AI in Industry
  • Interpretable Machine Learning
• 

  Fairness of AI
  tl;dr: An introduction to bias and fairness in AI Systems.
  [slides]
  

  Suggested Readings:

  • Fairness Tutorial
  • Fairness and machine learning