Advanced Artificial Intelligence (CECS 551)

Course Outline

This course is an in-depth exploration of Artificial Intelligence, designed to provide a comprehensive understanding of the principles and practical applications of AI. It begins with a foundational review of Probability, Statistics, and Linear Algebra, crucial for grasping AI algorithms. The course then delves into various aspects of AI, including Search Algorithms, Logical Inference, and Inference under Uncertainty, providing insights into how AI systems process information and make decisions. We also dedicate time to Machine Learning and Advanced Deep Learning, where students learn about different learning models and neural network architectures. Key applications of AI in fields like Natural Language Processing and Computer Vision, are showcased. The course involves programming projects in Python.

Learning Outcomes

The primary objectives of this course is for the students to be able to:

• Understand and utilize AI algorithms
• Construct AI-based solutions to a variety of practical problems.
• Critically analyze the present trends and challenges in AI research.

Modules

Probability, Statistics, and Linear Algebra Review

• Basic concepts of probability: random variables, probability distributions, expected value.
• Conditional, joint, and marginal distributions.
• Statistical measures: mean, median, mode, standard deviation, and correlation.
• Vector spaces, Norms, and Matrix calculation.

Search Algorithms

• Search Problems.
• Graph search algorithms: Depth-First, Breadth-First, and Greedy Search.
• $A^*$ Search, Minimax, and $\alpha-\beta$ Pruning.

Logical Inference

• Propositional Logic.
• Inference on a knowledge base.
• Model Checking and other methods of resolution.
• First Order Logic.

Inference Under Uncertainty

• Bayesian Networks.
• Sampling methods: Direct and Weighted sampling.
• Hidden Markov Models: Gibbs and MCMC sampling.

Finding Optimal Solutions

• Optimization methods: Hill Climbing, Simulated Annealing, and other stochastic methods.
• Linear Programming.
• Constraint Satisfaction problems.

Machine learning for AI

• Supervised Learning: Nearest-Neighbor Classification, Linear models, Support Vector Machines.
• Unsupervised Learning: k-means Clustering.
• Reinforcement Learning: Markov Decision Processes, Q-Learning.
• Neural Networks: Layers, activation, back-propagation, and training

Advanced Deep Learning for AI

• Generative Models: GANs, Normalizing Flows, and Diffusion models.

Natural Language Processing

• Transformer architecture
• Large Language models (GPT, BERT)
• Sentiment Analysis, Machine translation, and Text Generation

Computer Vision

• Convolutional Neural Networks
• Image Recognition and Image Generation

Learning Resources

Readings will be assigned from open educational resources based on the topic. If you are inteersted in building foundational knowledge in machine learning and AI, here are a number of excellent books you can read:

• Artificial Intelligence: A Modern Approach is a comprehensive and easy-to-approach reference for AI.
• Understanding Deep Learning by Simon J.D. Prince. Published by MIT Press 2023, also available from authors website. This new book offers an in-depth exploration of classical and cutting-edge aspects of deep learning.
• Pattern Recognition and Machine Learning, by C.M. Bishop. Available from Microsoft Research. This is the book if you want to learn machine leaning theory at a deeper level of understanding.

Special Accommodations

We are committed to providing equal opportunities for all students in our courses. If you require any special accommodations due to a documented disability, medical condition, or other circumstance that may affect your ability to fully participate in the course, please notify me as early as possible. Also, please contact the Bob Murphy access center (BMAC) for more information. BMAC personnel will work with students to identify a reasonable accommodation in partnership with appropriate academic offices and medical providers. Only approved BMAC petitions will be accommodated.

Any student who is facing academic or personal challenges due to difficulty in affording groceries/food and/or lacking a safe and stable living environment is urged to contact the CSULB Student Emergency Intervention & Wellness Program. Additional resources are available via Basic Needs Program.For mental health assistance please check out CSULB Counseling and Psychological Services (CAPS).

Academic Integrity

Before attending the class, please make sure that you have invested some time to read about CSULB academic integrity policy here. Of particular importance, are the definitions of Plagiarism and Cheating, and the steps the university will take to adjudicate academic integrity cases.

Work that you submit is assumed to be original unless your source material is documented appropriately, using proper citation. This includes using AI assistance in writing, coding and solving problems. At a minimum, any student caught violating Academic Integrity Policy will receive no credit for the work concerned and one grade lower letter grade.

Disclaimer

Please be aware that this course outline may change without prior notice. There may be instances where adjustments are needed for the course content, schedule, or grading policy. As a result, it is important that students check the official course syllabus on canvas regularly for the latest updates.