MS Artificial Intelligence

AI 602 Programming in Python
Problem solving, algorithmic design, and implementation using the Python programming language are presented. Topics include fundamental data types and associated collection data types, I/O processing, conditional and loop constructs, use and implementation of functions. This first part of the course is complemented with a through presentation of Object-Oriented programming. Select advanced features for both procedural programming and Object-Oriented programming are introduced. Throughout the course, good programming styles and sound program development are emphasized. Three credits; one-hour laboratory.
Credits: 3
Every Fall and Spring

AI 632 Algorithms and Data Structures in Python
A comprehensive study of the design and analysis of efficient data structures and algorithms in Python. The course provides the fundamentals of data structures and algorithms, including their design, analysis and implementations. Fundamental data abstractions include: linear lists; stacks; queues and deques; priority queues; multi-linked structures; trees and graphs; maps; hash tables; internal and external sorting and searching.  Three credits; one-hour laboratory. Prerequisite: AI 602
Credits: 3
Every Fall and Spring

AI 680 Artificial Intelligence: Present and Future
AI systems now outperform humans on tasks that were once taken to show great intelligence when undertaken by people (for example, playing chess). How far can this go in the future? What are the assumptions behind different approaches to AI? What dangers can there be from AI systems, and how should AI practitioners take these into account? The course gives a quick overview of the background and of contemporary work in symbolic AI, and looks at the relationship between statistical and 2 logical approaches to AI. It also addresses some of the philosophical and ethical issues that arise. The course surveys the state of the art in current AI, looking at systems and techniques in various subfields (eg, agents and reasoning; planning, constraints and uncertainty; google search and the semantic web; dialogue and machine translation; varieties of learning).  Three credits; one-hour laboratory.
Credits: 3
Every Fall and Spring

AI 681 Machine Learning & Pattern Recognition
This graduate course covers some fundamental theoretical concepts in machine learning, and common patterns for implementing methods in practice. The intended audience is those wanting the background required to begin research and development of machine learning methods. The course provides foundations of pattern recognition algorithms and machines, including statistical and structural methods. Data structures for pattern representation, feature discovery and selection, classification vs. description, parametric and non- parametric classification, supervised and unsupervised learning, use of contextual evidence, clustering, recognition with strings, and small sample-size problems. Three credits; one-hour laboratory.
Credits: 3
Every Fall and Spring

AI 682 Data Mining and Exploration
The aim of this course is to discuss modern techniques for analyzing, interpreting, visualizing and exploiting the data that is captured in scientific and commercial environments. The course will develop the ideas taught in various machine learning courses and discuss the issues in applying them to real-world data sets, as well as teaching about other techniques and data-visualization methods. The course will also feature case-study presentations and each student will undertake a mini-project on a real-world dataset.  The course will consist of two parts, the first part being a series of lectures on what is outlined below. It is anticipated that there will also be one or two guest lectures from data mining practitioners.  The second part will consist of student presentations of papers relating to relevant topics. Students will also carry out a practical mini-project on a real-world dataset. For both paper presentations and mini-projects, lists of suggestions will be available, but students may also propose their own, subject to approval from the instructor. A pre requisite of AI 681 is required. Three credits; one-hour laboratory.
Credits: 3
Every Fall and Spring

AI 683 Statistical Learning 
This course provides an introduction to the statistical methods commonly used in learning from data. The course combines methodology with theoretical foundations and their computational aspects. The course aims to assist you in designing good learning algorithms and analyzing their statistical properties and performance guarantees. Fundamental principles and techniques of probabilistic thinking, statistical modeling, and data analysis are introduced. Topics covered include basic probability and statistics including events, conditional probabilities, Bayes theorem, random variables, probability distributions, and hypothesis testing. Building on these concepts, the course provides an in depth of coverage of supervised learning from data with focus on regression and classification methods. A few key unsupervised learning methods such as clustering (K-means and Hierarchical clustering) are covered.  R is used for computing throughout the course. Three credits; one-hour laboratory.
Credits: 3
Every Fall and Spring

AI 686 Automatic Speech Recognition
The course covers the theory and practice of automatic speech recognition (ASR), with a focus on the statistical approaches that comprise the state of the art. The course introduces the overall framework for speech recognition, including speech signal analysis, acoustic modelling using hidden Markov models, language modelling and recognition search. Advanced topics covered will include speaker adaptation, robust speech recognition and speaker identification. The practical side of the course will involve the development of a speech recognition system using a speech recognition software toolkit. Three credits; one-hour laboratory. A pre requisite of AI 681 is required.
Credits: 3
Every Fall and Spring

AI 687 AI and Machine Learning in Bioinformatics 
The digital revolution has seen a dramatic increase in data collection in various disciplines of health sciences. The challenge of big and wide data is especially pronounced in the biomedical space where, for example, whole genome sequencing technology enables researchers to interrogate all 3 billion base pairs of the human genome. With an expected 50% of the world’s population likely to have been sequenced by 2025, the resulting datasets may surpass those generated in Astronomy, Twitter and YouTube combined. Machine Learning approaches are hence necessary to gain insights from these enormous and highly complex modern datasets enabling the training of very sophisticated Machine Learning models under the context of Artificial intelligence. The course addresses various topics of Machine Learning approaches that have been applied under the genomic revolution. Emphasis are placed on Machine Learning algorithms to recognize patterns in DNA sequences such as pinpointing the locations of transcription start sites (TSSs), identifying the importance of junk DNA in the genome and identifying untranslated regions (UTRs), introns and exons in eukaryotic chromosomes.  The input data can include the genomic sequence, gene expression profiles across various experimental conditions or phenotypes, protein-protein interaction data, synthetic lethality data, open chromatin data, and ChIP-seq data. Three credits; one-hour laboratory. Prerequisites:  AI 681
Credits: 3
Every Fall and Spring

AI 688 Image and Vision Computing 
The course addresses the analysis of images and video in order to recognize, reconstruct and model objects in the three-dimensional world. Emphasis is placed on studying the geometry of image formation; basic concepts in image processing such as smoothing, edge and feature detection, color, and texture; motion estimation; segmentation; stereo vision; 3-D modeling; and statistical recognition. Three credits; one-hour laboratory. A pre requisite of AI 681 is required.
Credits: 3
Every Fall and Spring

AI 689 Computational Neuroscience, Cognition and Artificial Intelligence 
The course addresses foundational tools that connect cognitive science and computational neuroscience with artificial intelligence. Emphasis are placed on computational models that mimic brain information processing during perceptual, cognitive and control tasks tested with brain and behavioral data. Computational approaches to understanding cognitive processes, using massively parallel networks are studied. Biologically-inspired learning rules for connectionist networks and their application in connectionist models of perception, memory and language are discussed. Three credits; one-hour laboratory. A pre requisite of AI 681 is required.
Credits: 3
Every Fall and Spring

AI 698 Thesis I
Preparation of a thesis under the supervision of a faculty adviser. The completed thesis is evaluated by the Department's graduate Curriculum Committee.
Credits: 3
Every Fall and Spring

AI 699 Thesis I
Preparation of a thesis under the supervision of a faculty adviser. The completed thesis is evaluated by the Department's graduate Curriculum Committee.
Credits: 3
Every Fall and Spring

AI 700 Applicable Deep Learning
Deep Learning is one of the most highly sought-after skills in AI. In this course, you will learn the foundations of Deep Learning, understand how to build neural networks, and learn how to lead successful machine learning projects. You will learn about Convolutional networks, RNNs, LSTM, Adam, Dropout, BatchNorm, Xavier/He initialization, and more.  Deep learning algorithms extract layered high-level representations of data in a way that maximizes performance on a given task. For example, asked to recognize faces, a deep neural network may learn to represent image pixels first with edges, followed by larger shapes, then parts of the face like eyes and ears, and, finally, individual face identities. Deep learning is behind many recent advances in AI, including Siri’s speech recognition, Facebook’s tag suggestions and self-driving cars. You will work on case studies from healthcare, autonomous driving, sign language reading, music generation, and natural language processing. You will master not only the theory, but also see how it is applied in industry. You will practice all these ideas in Python and in TensorFlow. After this course, you will likely find creative ways to apply it to your work. This course culminates in a capstone project. Three credits; one-hour laboratory. Prerequisite: AI 681
Credits: 3
Every Fall and Spring

AI 701 Intelligent Autonomous Robotics
This course covers basic topics in autonomous robotics/systems. Intelligent autonomous robots and systems can sense their environment, make decisions on how to act based on the sensations, and execute these actions without human aid or intervention. The main focus of the course is on designing and building robotic systems that navigate independently in complex environments. It is a programming intensive course which requires teamwork and collaboration, the use of the robotic hardware interface and the implementation of several algorithms to address key areas for effective sensor processing, vision processing, and autonomous decision making in a physical setting or a 3D simulated environment. Three credits; one-hour laboratory. A pre requisite of AI 688 and AI 700 is required.
Credits: 3
On Occasion

AI 790 Special Topics in Artificial Intelligence I
A course for presenting timely advanced topics in Artificial Intelligence, including research topics. Topics may vary from year to year according to the interest of faculty and students. The course contents and objectives are aligned with the overall program learning goals. The course requires formal submission of the course topic and a detailed syllabus for department and faculty reviews and approvals. Three credits; one-hour laboratory.
Credits: 3
On Occasion

AI 791 Special Topics in Artificial Intelligence I
A course for presenting timely advanced topics in Artificial Intelligence, including research topics. Topics may vary from year to year according to the interest of faculty and students. The course contents and objectives are aligned with the overall program learning goals. The course requires formal submission of the course topic and a detailed syllabus for department and faculty reviews and approvals. Three credits; one-hour laboratory.
Credits: 3
On Occasion