Font Size

SCREEN

Cpanel

Computational Intelligence

Graduate Certificate Program

Computational Intelligence

Program Description:
Recent advances in information technology and the increased level of interconnectivity that society has achieved through Internet and broadband communication technology created systems that are very much different. The world is facing an increasing level of systems integration leading towards Systems of Systems (SoS) that adapt to changing environmental conditions. The number of connections between components, the diversity of the components and the way the components are organized can lead to different emergent system behavior. Computational Intelligence tools are an integral part of these systems in enabling adaptive capability in their design and operation.
This graduate certificate program provides practicing engineers the opportunity to develop the necessary skills in the use and development of computational intelligence algorithms based on evolutionary computation, neural networks, fuzzy logic, and complex systems theory. Engineers can also learn how to integrate common sense reasoning with computational intelligence elective courses such as data mining and knowledge discovery.

Curriculum*:
The certificate program consists of four courses, two core courses and two elective courses. In order to receive a Graduate Certificate, the student must have an average graduate cumulative grade point of 3.0 or better in the certificate courses taken.

Core Course:

Comp Eng 5310/ Elec Eng 5310/ Sys Eng 5211: Computational Intelligence

Select one course from the following:

Comp Sci 5400: Introduction to Artificial Intelligence
Comp Sci 5401: Evolutionary Computing
Sys Eng 5212/Elec Eng 5370: Introduction to Neural Networks and Applications

Elective Courses (select two courses not taken as a core course):

Elec Eng / Comp Eng / Sys Eng 5001: Evolvable Hardware
Comp Sci 5400: Introduction to Artificial Intelligence
Comp Sci 5401: Evolutionary Computing
Comp Sci 6400: Advanced Topics in Artificial Intelligence
Comp Sci 6401: Advanced Evolutionary Computing
Sys Eng 6215/ Comp Eng 6320 / Elec Eng 6360: Adaptive Critic Designs
Comp Sci 6402 / Sys Eng 6216 / Comp Eng 6302: Advanced Topics in Data Mining
Elec Eng 5320: Neural Networks for Control
Sys Eng 5212 / Elec Eng 5310: Introduction to Neural Networks and Applications
Mech Eng 6447 / Comp Eng 6310 / Eng Mgt 6410 / Aero Eng 6447 / Comp Sci 6202: Markov Decision Processes
Sys Eng 6213: Advanced Neural Networks

* Curriculum is subject to change. Please contact the department for up-to-date information on courses. Other courses approved by the department may be substituted for any of the above listed courses on a case-by-case basis. The administrative coordinators must approve the substitution prior to enrolling in the course.

Course Descriptions:

Comp Eng 5310/Sys Eng 5211: Computational Intelligence
Introduction to Computational Intelligence (CI), Biological and Artificial Neuron, Neural Networks, Evolutionary Computing, Swarm Intelligence, Artificial Immune Systems, Fuzzy Systems, & Hybrid Systems. CI application case studies covered include digital systems, control, power systems, forecasting and time-series predictions. Prerequisite: STAT 3117. (Co-listed with Elec Eng 5310).

Sys Eng 5212 / Elec Eng 5370: Introduction to Neural Networks & Applications
Introduction to artificial neural network architectures, adaline, madaline, back propagation, BAM, and Hopfield memory, counter-propagation networks, self-organizing maps, adaptive resonance theory, are the topics covered. Students experiment with the use of artificial neural networks in engineering through semester projects. Prerequisite: Math 3304 or 3329. (Co-listed with Comp Sci 378, Elec Eng 5370).

Elec Eng / Comp Eng / Sys Eng 5001: Evolvable Hardware
This course deals with adaptive evolvable systems operating in a changing environment. Components/building blocks approach for the design of evolvable systems and the mathematical theory of evolvable machines and the idea of virtual reconfigurable circuits for the design of more adaptive, competitive and innovative engineering products will be taught. Prerequisites: Comp Eng 5310/ Elec Eng 5310/ Sys Eng 5211.

Comp Sci 5400: Introduction to Artificial Intelligence
A modern introduction to AI, covering important topics of current interest such as search algorithms, heuristics, game trees, knowledge representation, reasoning, computational intelligence, and machine learning. Students will implement course concepts covering selected AI topics. Prerequisite: Comp Sci 2500.

Comp Sci 5401: Evolutionary Computing
Introduces evolutionary algorithms, a class of stochastic, population-based algorithms inspired by natural evolution theory (e.g., genetic algorithms), capable of solving complex problems for which other techniques fail. Students will implement course concepts, tackling science, engineering and/or business problems. Prerequisites: Comp Sci 2500 and a statistics course.

Comp Sci 6400: Advanced Topics in Artificial Intelligence
Objectives of work in artificial intelligence simulation of cognitive behavior and self-organizing systems. Heuristic programming techniques including the use of list processing languages. Survey of examples from representative application areas. The mind-brain problem and the nature of intelligence. Class and individual projects to illustrate basic concepts. Prerequisite: Comp Sci 5400.

Comp Sci 6401: Advanced Evolutionary Computing
Advanced topics in evolutionary algorithms, a class of stochastic, population-based algorithms inspired by natural evolution theory, capable of solving complex problems for which other techniques fail. Students will conduct challenging research projects involving advanced concept implementation, empirical studies, statistical analysis, and paper writing. Prerequisite: Comp Sci 5401.

Sys Eng 6215/Comp Eng 6320/Elec Eng 6360: Adaptive Critic Designs
Review of Neurocontrol and Optimization, Introduction to Approximate Dynamic Programming (ADP), Reinforcement Learning (RL), Combined Concepts of ADP and RL - Heuristic Dynamic Programming (HDP), Dual Heuristic Programming (DHP), Global Dual Heuristic Programming (GDHP), and Case Studies. Prerequisite: Elec Eng 5370 Neural Networks or equivalent (Computational Intelligence Comp Eng 4001). (Co-listed with Comp Eng 6320, Mech Eng 6458, Aero Eng 6458 and Sys Eng 6215).

Comp Sci 6402/Sys Eng 6216/Comp Eng 6302: Advanced Topics in Data Mining
Advanced topics of current interest in the field of data mining. This course involves reading seminal and state-of-the-art papers as well as conducting topical research projects including design, implementation, experimentation, analysis, and written and oral reporting components. Prerequisite: A "C" or better grade in Comp Sci 5001 Introduction to Data Mining. Co-listed with Comp Eng 6302 and Sys Eng 6216.

Elec Eng 5320: Neural Networks for Control
Introduction to artificial neural networks and various supervised and unsupervised learning techniques. Types of neural nets architecture used in control. Identification and adaptive control using neural networks. Case studies and laboratory projects. Prerequisite: Elec Eng 3320.

Sys Eng / Comp Eng / Elec Eng 6360: Adaptive Critic Designs
Review of Neurocontrol and Optimization, introduction to Approximate Dynamic Programming (ADP), Reinforcement Learning (RL), combined concepts of ADP and RL, Heuristic Dynamic Programming (HDP), Duel Heuristic Programming (DHP), Global Dual Heuristic Programming (GDHP) and case studies. Prerequisites: Sys Eng/ Comp Eng/Elec Eng 5310.

Comp Sci 6402 / Sys Eng 6216 / Comp Eng 6302: Advanced Topics in Data Mining
Advanced topics of current interest in the field of data mining. This course involves reading seminal and state-of-the-art papers as well as conducting topical research projects including design, implementation, experimentation, analysis, and written and oral reporting components. Prerequisite: A "C" or better grade in Comp Sci 5001 Introduction to Data Mining. (Co-listed with Comp Eng 6302 and Sys Eng 6216).

Mech Eng 6447/ Comp Eng 6310/ Eng Mgt 6410/ Aero Eng 6447/ Comp Sci 6202: Markov Decision Processes
Introduction to Markov Decision Processes & Dynamic Programming. Application to Inventory Control & other optimization & control topics.

Sys Eng 6213: Advanced Neural Networks
Advanced artificial neural network architectures, namely; Radial-Basis Function Networks, Support Vector Machines, Committee Machines, Principal Components Analysis, Information-Theoretic Models, Stochastic Machines, Neurodynamic Programming, and Temporal Processing are the topics covered. Prerequisite: Sys Eng 5212 or equivalent neural network course.

 

Admission Requirements

Admissions Requirements: Systems Engineering, Computer Science Departments
This certificate program is open to all persons holding a BS, MS, or PhD degree and who have a minimum of 12 months of professional employment experience or are currently accepted into a graduate degree program at LCIT. Students admitted to the certificate program will have non-degree graduate status but will earn graduate credit for the courses they complete.

 

Admissions Requirements: Department of Electrical and Computer Engineering

  • BS degree in any field of engineering
  • A minimum of 24 months of post BS professional work experience
  • GPA of 3.0 or better in the BS degree
  • Average GPA of 3.0 or better (a grade of B or better) in the CT courses
  • 3 years to complete the CT
  • Employed while taking CT courses

Once admitted to the program, the student must take four designated courses as given above. In order to receive a Graduate Certificate, the student must have an average graduate grade point average of 3.0 or better in the certificate courses taken. Students admitted to the certificate program will have non-degree graduate status; however, if they complete the four-course sequence with a grade of B or better in each of the courses taken, they will be admitted to the MS program in electrical or computer engineering if they apply. The certificate courses taken by students admitted to the MS program will count towards their master's degrees. Students who do not have all of the prerequisite courses necessary to take the courses in the certificate program will be allowed to take "bridge" courses at either the graduate or undergraduate level to prepare for the formal certificate courses. Once admitted to the program, a student will be given three years to complete the program so long as he/she maintains a B average in the courses taken.

Contact us

Here is our Contact info :

  •     Phone: +442035198338
  •     Fax: +442035198338

Social Networks

Follow us & get in touch.
 

Newsletter

Make sure you dont miss interesting happenings by joining our newsletter program.