2. Professors
  3. Teaching

NATURAL COMPUTATION

Angelo MARCELLI NATURAL COMPUTATION

0623200018
DEPARTMENT OF INFORMATION AND ELECTRICAL ENGINEERING AND APPLIED MATHEMATICS
EQF7
INFORMATION ENGINEERING FOR DIGITAL MEDICINE
2024/2025



YEAR OF COURSE 2
YEAR OF DIDACTIC SYSTEM 2022
SPRING SEMESTER
CFUHOURSACTIVITY
432LESSONS
216LAB
ANGELO MARCELLI T Curriculum
ANTONIO DELLA CIOPPA Curriculum
Objectives
MODELS AND COMPUTATIONAL TECHNIQUES INSPIRED BY NATURE FOR SOLVING COMPLEX PROBLEMS AND OF STRENGTHS/WEAKNESSES BETWEEN THE DIFFERENT APPROACHES DISCUSSED IN THE LECTURES.

KNOWLEDGE AND UNDERSTANDING
BASIC OF THE MECHANISMS AND THE PRINCIPLES OF THE DARWINIAN EVOLUTION, THE IMMUNE SYSTEM, THE SWARM INTELLIGENCE AND THE NEUROPHYSIOLOGY OF THE HUMAN BRAIN.COMPUTATIONAL MODELS AND THEIR IMPLEMENTATIONS. METHODS AND TECHNIQUES FOR PERFORMANCE EVALUATION. "BEST PRACTICES" FOR SELECTING THE MOST SUITABLE COMPUTATIONAL MODEL FOR A GIVEN APPLICATION.

APPLYING KNOWLEDGE AND UNDERSTANDING
COMPARATIVE PERFORMANCE ANALYSIS OF DIFFERENT COMPUTATIONAL METHODS FOR A GIVEN APPLICATION. USE OF THE "BEST PRACTICE" FOR SOLVING OPTIMIZATION AND MACHINE LEARNING PROBLEMS.
Prerequisites
COMPUTER SYSTEM ORGANIZATION, PERFORMANCE MEASURES OF ITS COMPONENTS, ALGORITHMS AND DATA STRUCTURES
Contents
TEACHING UNIT 1: INTRODUCTION TO NATURAL COMPUTATION
(LECTURE/PRACTICE/LABORATORY HOURS 2/0/0)
- 1 (2 HOURS LECTURE): THE NATURAL COMPUTATION PARADIGM AND NATURAL COMPUTATION ALGORITHMS - BASIC CONCEPTS: AGENT, AUTONOMY, INTERACTIVITY, EVALUATION AND FEEDBACK, LEARNING
KNOWLEDGE AND UNDERSTANDING SKILLS: UNDERSTANDING OF THE PARADIGMS UNDERLYING NATURAL COMPUTATION
APPLIED KNOWLEDGE AND UNDERSTANDING SKILLS: KNOWING HOW TO CLASSIFY NATURAL COMPUTATION ALGORITHMS BASED ON THE PARTICULAR PARADIGM ADOPTED


TEACHING UNIT 2: EVOLUTIONARY COMPUTATION
(HOURS LECTURE/PRACTICE/LABORATORY 6/0/4)
- 2 (2 HOURS LECTURE): FUNDAMENTALS OF EVOLUTIONARY BIOLOGY: SELECTION, RECOMBINATION AND MUTATION-INTRODUCTION TO EVOLUTIONARY ALGORITHMS
- 3 (2 HOURS LECTURE): GENETIC ALGORITHMS AND DIFFERENTIAL EVOLUTION
- 4 (2 HOURS LECTURE): GENETIC PROGRAMMING
- 5 (2 HOURS LAB): APPLICATION OF DIFFERENTIAL EVOLUTION TO OPTIMIZATION PROBLEMS
- 6 (2 HOURS LAB): APPLICATION OF GENETIC PROGRAMMING TO OPTIMIZATION PROBLEMS AND LEARNING
KNOWLEDGE AND UNDERSTANDING SKILLS: ACQUIRE KNOWLEDGE RELATED TO THE FUNDAMENTAL ELEMENTS OF EVOLUTIONARY COMPUTATION
APPLIED KNOWLEDGE AND UNDERSTANDING SKILLS: KNOW HOW TO APPLY EVOLUTIONARY COMPUTATION TO VARIOUS TYPES OF REAL-WORLD PROBLEMS


TEACHING UNIT 3: ARTIFICIAL IMMUNE SYSTEMS
(HOURS LECTURE/PRACTICE/LABORATORY 6/0/2)
- 7 (2 HOURS LECTURE): FUNDAMENTALS OF IMMUNOLOGY: ANTIGENS AND ANTIBODIES
- 8 (2 HOURS LECTURE): ARTIFICIAL IMMUNE SYSTEMS
- 9 (2 HOURS LECTURE): NEGATIVE SELECTION, CLONALG
- 10 (2 HOURS LAB): APPLICATION OF NEGATIVE SELECTION AND CLONALG TO OPTIMIZATION AND CLASSIFICATION PROBLEMS
KNOWLEDGE AND UNDERSTANDING SKILLS: ACQUIRE KNOWLEDGE ABOUT THE BASIC ELEMENTS OF ARTIFICIAL IMMUNE SYSTEMS
APPLIED KNOWLEDGE AND UNDERSTANDING SKILLS: KNOW HOW TO APPLY ARTIFICIAL IMMUNE SYSTEMS TO VARIOUS TYPES OF REAL-WORLD PROBLEMS


TEACHING UNIT 4: SWARM INTELLIGENCE
(HOURS LECTURE/PRACTICE/LABORATORY 6/0/2)
- 11 (2 HOURS LECTURE): FUNDAMENTALS OF SOCIAL INTELLIGENCE
- 12 (2 HOURS LECTURE): ANT COLONY
- 13 (2 HOURS LECTURE): PARTICLE SWARM OPTIMIZATION
- 14 (2 HOURS LAB): APPLICATION OF ANT COLONY AND PARTICLE SWARM TO OPTIMIZATION PROBLEMS AND OPTIMAL PATH FINDING
KNOWLEDGE AND UNDERSTANDING SKILLS: ACQUIRE KNOWLEDGE RELATED TO THE FUNDAMENTAL ELEMENTS OF SWARM INTELLIGENCE
APPLIED KNOWLEDGE AND UNDERSTANDING SKILLS: KNOW HOW TO APPLY SWARM INTELLIGENCE TO VARIOUS TYPES OF REAL-WORLD PROBLEMS


TEACHING UNIT 5: NEUROEVOLUTION
(LECTURE/PRACTICE/LAB HOURS 2/0/2)
- 15 (2 HOURS LECTURE): FUNDAMENTALS OF NEUROEVOLUTION: EVOLUTIONARY ALGORITHMS FOR AUTOMATIC SYNTHESIS OF NEURAL NETWORKS
- 16 (2 HOURS LAB): APPLICATION OF NEUROEVOLUTION TO REINFORCEMENT LEARNING PROBLEMS
KNOWLEDGE AND UNDERSTANDING SKILLS: ACQUIRE KNOWLEDGE RELATED TO THE FUNDAMENTAL ELEMENTS OF NEUROEVOLUTION
APPLIED KNOWLEDGE AND UNDERSTANDING SKILLS: KNOW HOW TO APPLY NEUROEVOLUTION TO VARIOUS TYPES OF REAL-WORLD PROBLEMS


TEACHING UNIT 6: COMPUTATIONAL NEUROSCIENCE
(HOURS LECTURE/PRACTICE/LABORATORY 6/0/2)
- 17 (2 HOURS LECTURE): FUNDAMENTALS OF NEUROSCIENCE
- 18 (2 HOURS LECTURE): MODELS OF BRAIN STRUCTURES
- 19 (2 HOURS LECTURE): INTEGRATION OF MODELS
KNOWLEDGE AND UNDERSTANDING SKILLS: ACQUIRE KNOWLEDGE RELATED TO THE FUNDAMENTAL ELEMENTS OF COMPUTATIONAL NEUROSCIENCE
APPLIED KNOWLEDGE AND UNDERSTANDING SKILLS: ...


TEACHING UNIT 7: FINAL PROJECT
(HOURS LECTURE/PRACTICE/LABORATORY 2/0/6)
- 20 (2 HOURS LECTURE): SPECIFICATIONS OF THE FINAL PROJECT AND RELATED TOOLS
- 21 (8 HOURS LAB): SUPERVISION OF FINAL PROJECT
KNOWLEDGE AND UNDERSTANDING SKILLS: Organization of team working. Definition of project tasks and milestones.
APPLIED KNOWLEDGE AND UNDERSTANDING SKILLS: DESIGN and IMPLEMENTATION of a Natural Computing algorithm for solving a real-world prediction problem.




TOTAL HOURS LECTURE/PRACTICE/LABORATORY 30/0/18
Teaching Methods
THE COURSE INCLUDES LECTURES, CLASSROMM PRACTICE AND LABORATORY ACTIVITIES. DURING CLASSROMM RECITATION, THE MAIN FEATURES OF CONSIDERED MODEL IN DEVELOPING THE FINAL PROJECT ARE PRESENTED AND DISCUSSED. IN THE LAB, THE STUDENTS ARE GROUPED IN TEAMS, AND EACH TEAM MUST DESIGN AND IMPLEMENT A SOLUTION FOR A PROBLEM THE TEAM HAS SELECTED AMONG THOSE PRESENTED DURING RECITATIONS OR PROPOSED BY THE TEAM ITSELF.
Verification of learning
THE FINAL EVALUATION IS CARRIED OUT BY AN ORAL EXAMINATION ON THE TOPICS NOT DIRECTLY RELATED WITH THE FINAL PROJECT AND THE PRESENTAZION OF THE DESIGN WORK. THE FINAL GRADE IS THE WEIGHTED SUM OF THE DESIGN (40%), ITS PRESENTATION (20%) AND THE ORAL EXAMINATION.
Texts
L. NUNES DE CASTRO - FUNDAMENTALS OF NATURAL COMPUTING,CHAPMAN & HALL/CRC; 1 EDITION, 2006.
A. BRABAZON, M. O'NEILL AND S. MCGARRAGHY, NATURAL COMPUTING ALGORITHMS, SPRINGER, 2015

SUPPLEMENTARY TEACHING MATERIAL WILL BE AVAILABLE ON THE UNIVERSITY E-LEARNING PLATFORM (HTTP://ELEARNING.UNISA.IT) ACCESSIBLE TO STUDENTS USING THEIR OWN UNIVERSITY CREDENTIALS.

ADDITIONAL READING:
DANA H. BALLARD, BRAIN COMPUTATION AS HIERARCHICAL ABSTRACTION, MIT PRESS, 2015"
More Information
THE COURSE IS HELD IN ENGLISH.
  BETA VERSION Data source ESSE3 [Ultima Sincronizzazione: 2024-11-18]