The language of sets, propositional and predicate logic. Methods of proof including mathematical induction. Linear equations, matrices and Gaussian elimination. Vector spaces, linear independence, basis and dimension. Linear transformations, orthogonality, Gram-Schmidt orthogonalization. Eigenvalues, eigenvectors and diagonalization.

Foundational concepts in artificial intelligence, including knowledge representation and reasoning, machine learning, and neural networks. Introduction to the function, employment, and limitations of language models (LLMs), and proper LLM usage in coding tasks.

Artificial Intelligence System Specification and Design; AI software libraries and tools; Project Management; Artificial Intelligence System Architecture; Incremental Product Delivery; Prototyping; Evaluation; Team projects. Additional work required for graduate students.

Artificial Intelligence System Development; Incremental Product Delivery; Evaluation; Maintenance; Team projects; Additional work required for graduate students.

Computational and hardware foundations of ML; complexity and performance analysis of ML models; modern computer architectures; FPGA-based acceleration; model optimization techniques and their impacts. Additional work required for graduate students.

Feature extraction; Supervised and unsupervised learning; Bias-variance trade-off; Linear, logistic, and nonlinear regression; Decision trees and ensemble models; Neural networks; Deep Learning. Additional work required for graduate students.

Core artificial intelligence algorithms, including tree search and constraint satisfaction, automated reasoning, probabilistic models and Monte-Carlo methods, reinforcement learning, and automatic differentiation. Additional work is required for graduate students.

Exploration of a problem, or problems, in depth, individual independent study upon a plan submitted by the student. Admission by consent of supervising instructor(s) and the department.