Techniques in Artificial Intelligence (SMA 5504)
Graduate introduction to first-order logic, planning, supervised learning, and Bayesian network inference and learning.
Search titles, authors, subjects and dates from across the DARE African Knowledge Repository.
47 resources found in the repository.
Graduate introduction to first-order logic, planning, supervised learning, and Bayesian network inference and learning.
Introduces clinical data and ML for risk stratification, disease progression, precision medicine, diagnosis, and workflow improvement.
Covers holistic matrix calculus and derivatives of matrix factorizations for machine learning and large-scale optimization.
Studies representations, contours, level sets, deformation fields, manifold fitting, Markov random fields, EM, and clustering for image analysis.
Reviews linear algebra with applications to probability, statistics, optimization, signal processing, and deep learning.
Provides a mathematically rigorous introduction to pattern identification in data and analysis of ML methods.
Graduate NLP course covering syntactic, semantic, and discourse models with machine-learning and corpus-based methods.
Graduate introduction to statistical inference with probabilistic graphical models, foundational for ML, AI, vision, control, and signal processing.
Presents real-world analytics examples using data mining, dynamic optimization, and simulation.
Covers supervised learning, regularization, SVMs, VC theory, boosting, feature selection, and vision/text/bioinformatics applications.
Introduces nonlinear dynamics and computational control of underactuated mechanical systems with examples in legged locomotion and flying machines.
Graduate introduction to discourse structure, coherence, plan recognition, text segmentation, symbolic and ML methods, and dialogue applications.