Artificial Intelligence for Medicine

Lecturer:

Tutor:

Supervisor:

Department of Cybernetics

Synopsis:

The aim of this course is to get the students knowledgeable about some of those special methods of Artificial Intelligence, which are applied in medicine mot often. This is the case of algorithms for planning and scheduling, problems of cooperative problem solving by a group of partially independent agents and the tasks connected with robotics. Declarative programming is introduced as a tool for knowledge representation and reasoning. Special attention will be devoted to non-traditional evolutionary computational techniques of optimisation, state-space search, control and decision-making.

Requirements:

For successful completion of the course, it is necessary to present the resulst of the individual work to other students and explain the approaches used.

Syllabus of lectures:

1. Biomedical engineering and methods of Artificial Intelligence. Review of methods and tools

2. Declarative programming languages, logic programming. Prolog

3. Solving problems defined by constraints. Contrained logic programming CLP

4. Planning and scheduling

5. Multi-agent systems

6. Neural networks - basic principles, thei learning and set-up

7. Neural networks with backward propagation. Kohonen´s learning networks

8. Evolutionary computing - basic principles and operators

9. Genetic algorithms - function principles, problem representation, convergence

10. Genetic algorithms in constrained problems, special representations. Genetic programming - principles and comparison with genetic algorithms

11. Specific problems of evolutionary computing techniques, softcomputing applications

12. Robots and their typical tasks. Manipulator and an intelligent robot, their logic structure

13. Control of a manipulator - principal ideas, sensors used. Control af a robot - principal ideas, addvanced sensors

14. Telerobotics, man-robot inetrface, machines with partial intelligence

Syllabus of tutorials:

1. Organisational matters, seminars/labs detailed contents. State space in various AI tasks

2. Prolog

3. CLP

4. ProPlant multiagent system - presentation of a case study

5. Artificial life

6. Neural networks - part 1

7. Neural networks - part 2

8. Evolutionary computing (EC) - basic operators, their implementation, individual task of EC given

9. Individual work on the EC task - part 1

10. Individual work on the EC task - part 2

11. Presentation of individual work results - discussion on the results

12. Mechanics and kinematics of a robot - a review

13. Intelligent robots in medicine. Several demonstrations

14. Summary, (spare space)

Study Objective:

Study materials:

There in no text-book convering the course completely; any book on modern operating systems can be used. The lecturer will hint resources to particular topics.

1. Russell, S., Norving, P.: Artificial Intelligence. A Modern Approach. Prentice Hall, Englewood Cliffs, New Jersey 1995

Note:

Further information:

No time-table has been prepared for this course

The course is a part of the following study plans:

• Biomedical Engineering- structured studies (compulsory elective course)