Areas and faculty

Curriculum

CMSC 421 Introduction to Artificial Intelligence (3 credits). Prerequisites: A grade of C or better in CMSC330 and in CMSC351; and permission of the department or CMSC graduate student. Areas and issues in artificial intelligence, including search, inference, knowledge representation, learning, vision, natural languages, expert systems, robotics. Implementation and application of programming languages (e.g. LISP, PROLOG, SMALLTALK), programming techniques (e.g. pattern matching, discrimination networks) and control structures (e.g. agendas, data dependencies).

CMSC 720, Logic for Problem Solving (3 credits). Prerequisites: CMSC 421 or equivalent (or permission of instructor). Logic programming and its use in problem solving, natural language recognition and parsing, and robotics. The Prolog language. Meta-level and parallel logic programming. Expert systems. Term project in logic programming.

CMSC 721, Non-Monotonic Reasoning (3 credits). Prerequisites: CMSC 421 or equivalent (or permission of instructor). This course will survey several of the major standard formalisms for nonmonotonic reasoning, and also look at current research issues.

CMSC 722, Artificial Intelligence Planning (3 credits). Prerequisites: CMSC 421 or equivalent (or permission of instructor). A long-standing problem in AI is how to plan a set of actions to accomplish some desired goal. This course will cover the basic algorithms, important systems, and new directions in the field of AI planning systems.

CMSC 723 Computational Linguistics I (3 credits). Prerequisite: CMSC421 or equivalent; or permission of instructor. PhD Comp credit for CMSC723 or CMSC823, not both. Also offered as LING723. Not open to students who have completed LING645. Fundamental methods in natural language processing. Topics include: finite-state methods, context-free and extended context-free models of syntax; parsing and semantics interpretation; n-gram and Hidden Markov models, part-of-speech tagging; natural language applications such as machine translation, automatic summarization, and question answering.

CMSC 726 Machine Learning (3 credits). Prerequisite: CMSC 421 or equivalent or permission of instructor. Reviews and analyzes both traditional symbol-processing methods and genetic algorithms as approaches to machine learning. (Neural network learning methods are primarily covered in CMSC 727.) Topics include induction of decision trees and rules, version spaces, candidate elimination algorithm, exemplar-based learning, genetic algorithms, evolution under artificial selection of problem-solving algorithms, system assessment, comparative studies, and related topics.

CMSC 727, Neural Modeling (3 credits). Prerequisites: CMSC 421 or equivalent (or permission of instructor). Undergraduate calculus, linear algebra, and elementary probability theory are assumed. Fundamental methods of neural modeling. Surveys historical development and recent research results from both the computational and dynamical systems perspective. Logical neurons, perceptrons, linear adaptive networks, attractor neural networks, competitive activation methods, error back-propagation, self-organizing maps, and related topics. Applications in artificial intelligence, cognitive science, and neuroscience.

CMSC 773 Computational Linguistics II (3 credits). Prerequisite: CMSC723 or LING723; or permission of instructor. May only receive PhD Comp. credit for CMSC723 or CMSC823, not both. Also offered as LING773. Not open to students who have completed LING647. Formerly CMSC 828R. Natural language processing with a focus on corpus-based statistical techniques. Topics inlcude: stochastic language modeling, smoothing, noisy channel models, probabilistic grammars and parsing; lexical acquisition, similarity-based methods, word sense disambiguation, statistical methods in NLP applications; system evaluation.

CMSC 828, Advanced Topics. Prerequisite: Permission of instructor. Advanced topics selected by the faculty to suit the interest and background of students. May be taken for repeated credit. Here are some examples of courses that we have recently offered under this heading:

• Principles of Data Mining (3 credits). Prerequisites: CMSC 421, CMSC 424 and an undergraduate course in elementary probability/statistics (or permission of the instructor). Covers the fundamentals of data mining from both a statistical and database perspective. Topics include the statistical and machine learning foundations for data mining, fundamental data mining concepts and algorithms for tasks such as OLAP, association rules, clustering, etc., and research areas such as text mining, collaborative filtering, link analysis and mining in biological domains (as time permits).
• Evolutionary Computation and Artificial Life (3 credits). Prerequisites: CMSC 421 or equivalent (or permission of instructor). Survey and anlysis of biologically-inspired computing methods such as genetic algorithms/programming, cellular automata models, ant-colony optimization methods, L-systems, and swarm intelligence, along with their applications in AI.
• Software Agents (3 credits). Prerequisites: CMSC 421 or equivalent (or permission of instructor). This course describes what software agents are, how to build agents one at a time, how to specify and reason about groups of agents, how agents can communicate and collaborate with one another, and how agents may be used for a variety of commercial applications such as logistics and e-commerce.