Course Description: Presents foundational knowledge for designing artificial intelligence (AI) with reasoning capabilities and explores the latest advances in literature. Covers search algorithms, reinforcement learning, methods to design large language models (LLM) with reasoning capability, methods for symbolic and neuro-symbolic reasoning, and an overview of related areas.

Some of the Topics:

• A* search

• Reinforcement learning

  • Formulation and algorithms

  • Alpha Go, Alpha Zero, MuZero

• Design of LLM with reasoning capabilities

  • Improved Transformer and training methods published by DeepSeek, etc.

  • Chain of thought, Graph of thought

  • Reading the latest papers in the area

• Symbolic Reasoning

  • Logic

  • Reasoning using probabilistic graphical models

• Neuro-symbolic Reasoning

  • Fuzzy logic

  • Logic tensor networks, etc.

Syllabus

• If you do not meet the prerequisite but want to take the course, please email me at youjian.liu@colorado.edu

• syllabus pdf

• Canvas Course Site for quiz/homework submission and solution posting

Course Content (viewable with your CU account)

• Lecture notes on Onenote

• Lecture notes in pdf

• Shared Course Content (viewable) (lecture videos, slides, etc.)

• Shared Course Content (editable) (reading materials, project upload, etc.)

Homework Assignments (Due every Thursday)

• TBA