Ingegneria Informatica | COMPUTAZIONE NATURALE

cod. 0622700049

COMPUTAZIONE NATURALE

	0622700049
	DIPARTIMENTO DI INGEGNERIA DELL'INFORMAZIONE ED ELETTRICA E MATEMATICA APPLICATA
	EQF7
	COMPUTER ENGINEERING
	2017/2018

CURRICULUM INDIRIZZO INFORMATICA INDUSTRIALE Cohort 2016/2017

	YEAR OF COURSE 2
	YEAR OF DIDACTIC SYSTEM 2016
	SECONDO SEMESTRE

TEACHING UNITS

SSD	CFU	HOURS	ACTIVITY	TYPE OF ACTIVITY
ING-INF/05	4	32	LESSONS	OPTIONAL SUBJECTS
ING-INF/05	1	8	EXERCISES	OPTIONAL SUBJECTS
ING-INF/05	1	8	LAB	OPTIONAL SUBJECTS

PROFESSORS

	ANGELO MARCELLI T Curriculum
	ANTONIO DELLA CIOPPA Curriculum

	Objectives
	THE COURSE INTRODUCES MODELS AND COMPUTATIONAL TECHNIQUES INSPIRED BY NATURE FOR DEVELOPING NEW COMPUTATIONAL METHODS FOR SOLVING COMPLEX PROBLEMS. THE DIFFERENT APPROACHES PROPOSEDIN THE COURSE ARE PRESENTED THROUGH THE COMPARISON OF THEIR PERFORMANCE ON TEST PROBLEMS. THE COURSE INCLUDES AN INTRODUCTION TO THE NEUROPHYSIOLOGY AND EVOLUION OF THE HUMAN BRAIN. (KNOWLEDGE AND UNDERSTANDING) KNOWLEDGE OF THE BASICS OF NATURAL EVOLUTION MECHANISMS AND OF PRINCIPLES OF THE NEUROPHYSIOLOGY OF THE HUMAN BRAIN.UNDERSTANDING OF THE COMPUTATIONAL MODEL NATURAL EVOLUTION AND HUMAN BRAIN ACTIVITIES AND THEIR COMPUTATIONAL IMPLEMENTATIONS. KNOWLEDGE OF METHODS AND TECHNIQUES FOR PERFORMANCE EVALUATION. UNDERSTANDING OF THE "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 GIVEMN APPLICATION. USE OF TEH "BEST PRACTICE" FOR SETTING THE PARAMETERS OF EACH COMPUTATIONAL MODEL. (MAKING JUDGEMENT) CHOOSING AND APPLYING THE COMPUTATIONAL MODELS PRESENTED IN THE COURSE FOR PRODUCING HIGH QUALITY SOLUTIONS FOR HIGHLY COMPLEX PROBLEMS. BEING ABLE TO SELECT THE DATA, THE MEASURES AND THE PERFORMANCE INDEX TO RELIABLY ESTIMATE THE PERFORMANCE OF DIFFERENT POSSIBLE SOLUTIONS. COST/BENEFIT ANALYSIS OF THE PROPOSED SOLUTIONS. (COMMUNICATION SKILLS) SOCIAL SKILL FOR TEAMWORK, WRITTEN TECHNICAL DPCUMENTATION AND ORAL PRESENTATION OF THE DESIGN ACTIVITY.

THE COURSE INTRODUCES MODELS AND COMPUTATIONAL TECHNIQUES INSPIRED BY NATURE FOR DEVELOPING NEW COMPUTATIONAL METHODS FOR SOLVING COMPLEX PROBLEMS. THE DIFFERENT APPROACHES PROPOSEDIN THE COURSE ARE PRESENTED THROUGH THE COMPARISON OF THEIR PERFORMANCE ON TEST PROBLEMS. THE COURSE INCLUDES AN INTRODUCTION TO THE NEUROPHYSIOLOGY AND EVOLUION OF THE HUMAN BRAIN.
(KNOWLEDGE AND UNDERSTANDING)
KNOWLEDGE OF THE BASICS OF NATURAL EVOLUTION MECHANISMS AND OF PRINCIPLES OF THE NEUROPHYSIOLOGY OF THE HUMAN BRAIN.UNDERSTANDING OF THE COMPUTATIONAL MODEL NATURAL EVOLUTION AND HUMAN BRAIN ACTIVITIES AND THEIR COMPUTATIONAL IMPLEMENTATIONS. KNOWLEDGE OF METHODS AND TECHNIQUES FOR PERFORMANCE EVALUATION. UNDERSTANDING OF THE "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 GIVEMN APPLICATION. USE OF TEH "BEST PRACTICE" FOR SETTING THE PARAMETERS OF EACH COMPUTATIONAL MODEL.
(MAKING JUDGEMENT)
CHOOSING AND APPLYING THE COMPUTATIONAL MODELS PRESENTED IN THE COURSE FOR PRODUCING HIGH QUALITY SOLUTIONS FOR HIGHLY COMPLEX PROBLEMS. BEING ABLE TO SELECT THE DATA, THE MEASURES AND THE PERFORMANCE INDEX TO RELIABLY ESTIMATE THE PERFORMANCE OF DIFFERENT POSSIBLE SOLUTIONS. COST/BENEFIT ANALYSIS OF THE PROPOSED SOLUTIONS.
(COMMUNICATION SKILLS)
SOCIAL SKILL FOR TEAMWORK, WRITTEN TECHNICAL DPCUMENTATION AND ORAL PRESENTATION OF THE DESIGN ACTIVITY.

	Prerequisites
	COMPUTER SYSTEM ORGANIZATION, PERFORMANCE MEASURES OF ITS COMPONENTS, ALGORITHMS AND DATA STRUCTURES

	Contents
	INTRODUCTION (LECTURE: 2H - RECITATION 0H) THE PARADIGM OF NATURAL COMPUTATION - FUNDAMENTAL CONCEPTS: AGENT, AUTONOMY, INTERACTIVITY, EVALUATION AND FEEDBACK, LEARNING EVOLUTIONARY COMPUTATION (LECTURES: 6H - RECITATION: 2H) FOUNDATIONS OF NATURAL EVOLUTION: SELECTION, RICOMBINATION AND MUTATION - THE COMPUTATIONAL METAPHOR - GENETIC ALGORITHMS, EVOLUTIONARU ALGORITHMS AND GENETIC PROGRAMMING IMMUNE SYSTEMS (LECTURES: 6H - RECITATION: 2H) FUNDAMENTALS OF IMMUNOLOGY: ANTIGENS AND ANTIBODIES - THE COMPUTATIONAL METAPHOR - ARTIFICIAL IMMUNE SYSTEMS NEURAL NETWORKS (LECTURES: 6H - RECITATION: 2H) FOUNDAMENTALS OF NEUROPHYSIOLOGY - THE COMPUTATIONAL METAPHOR - NEURON COMPUTATIONAL MODELS - ARTIFICIAL NEURAL NETWORKS NEURAL NEWTORKS SYSTEMS (LECTURES: 8H - RECITATION: 2H) PRINCIPLES OF NEUROSCIENCE - THE COMPUTATIONAL METAPHOR NEUROCOMPUTATIONAL MODELS - LEVEL OF ABSTRACTION FINAL PROJECTS (LECTURES: 0H - LABORATORY: 12H) DESIGN, IMPLEMENTATION AND PERFORMANCE EVALUATION OF THE PROPOSED SOLUTION.

Contents

INTRODUCTION (LECTURE: 2H - RECITATION 0H)
THE PARADIGM OF NATURAL COMPUTATION - FUNDAMENTAL CONCEPTS: AGENT, AUTONOMY, INTERACTIVITY, EVALUATION AND FEEDBACK, LEARNING
EVOLUTIONARY COMPUTATION (LECTURES: 6H - RECITATION: 2H)
FOUNDATIONS OF NATURAL EVOLUTION: SELECTION, RICOMBINATION AND MUTATION - THE COMPUTATIONAL METAPHOR - GENETIC ALGORITHMS, EVOLUTIONARU ALGORITHMS AND GENETIC PROGRAMMING
IMMUNE SYSTEMS (LECTURES: 6H - RECITATION: 2H)
FUNDAMENTALS OF IMMUNOLOGY: ANTIGENS AND ANTIBODIES - THE COMPUTATIONAL METAPHOR - ARTIFICIAL IMMUNE SYSTEMS

NEURAL NETWORKS (LECTURES: 6H - RECITATION: 2H)
FOUNDAMENTALS OF NEUROPHYSIOLOGY - THE COMPUTATIONAL METAPHOR - NEURON COMPUTATIONAL MODELS - ARTIFICIAL NEURAL NETWORKS
NEURAL NEWTORKS SYSTEMS (LECTURES: 8H - RECITATION: 2H)
PRINCIPLES OF NEUROSCIENCE - THE COMPUTATIONAL METAPHOR
NEUROCOMPUTATIONAL MODELS - LEVEL OF ABSTRACTION
FINAL PROJECTS (LECTURES: 0H - LABORATORY: 12H)
DESIGN, IMPLEMENTATION AND PERFORMANCE EVALUATION OF THE PROPOSED SOLUTION.

	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.

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 EVALUATION OF THE DESIGN WORK. THE ORAL EXAMINATION AND THE PROJET PRESENTATION AND DISCUSS CONTRIBUTE WITH THE SAME WEIGHT TO THE FINAL SCORE, WHCIH REFERS TO A SCALE FROM 0 TO 30.

	Texts
	TEXT BOOK LEANDRO NUNES DE CASTRO - FUNDAMENTALS OF NATURAL COMPUTING,CHAPMAN & HALL/CRC; 1 EDITION, 2006. ADDITIONAL MATERIAL WILL BE AVAILABLE ON THE COURSE WEBSITE. ADDITIONAL READING: DANA H. BALLARD, BRAIN COMPUTATION AS HIERARCHICAL ABSTRACTION, MIT PRESS, 2015