MACHINE LEARNING

International Teaching MACHINE LEARNING

0622900024
DIPARTIMENTO DI INGEGNERIA DELL'INFORMAZIONE ED ELETTRICA E MATEMATICA APPLICATA
EQF7
DIGITAL HEALTH AND BIOINFORMATIC ENGINEERING
2021/2022



OBBLIGATORIO
YEAR OF COURSE 1
YEAR OF DIDACTIC SYSTEM 2018
SECONDO SEMESTRE
CFUHOURSACTIVITY
324LESSONS
324EXERCISES
324LAB


Objectives
THE COURSE PROVIDES METHODOLOGIES AND TOOLS FOR ANALYZING A PROBLEM, DESIGNING AN EFFICIENT SOLUTION. EVENTUALLY USING ADVANCED PROGRAMMING TECHNIQUES AND DATA STRUCTURES, AND IMPLEMENTING IT IN AN OBJECT-ORIENTED PROGRAMMING LANGUAGE.

KNOWLEDGE AND UNDERSTANDING
STUDENTS WILL LEARN ADVANCED PROGRAMMING TECHNIQUES AND DATA STRUCTURES. THEY WILL LEARN THE IMPLEMENTATION OF THE MOST RELEVANT DATA STRUCTURES INCLUDED IN STANDARD LIBRARIES. THEY WILL LEARN TO UNDERSTAND TERMINOLOGY USED IN THE CONTEXT OF ALGORITHM DESIGN.

APPLYING KNOWLEDGE AND UNDERSTANDING
STUDENTS WILL LEARN TO USE PROPOSED PROGRAMMING TECHNIQUES AND ADVANCED DATA STRUCTURES TO SOLVE COMPLEX PROBLEMS. THEY WILL BE ABLE TO IMPLEMENT ALGORITHMS AND DATA STRUCTURES IN AN OBJECT-ORIENTED PROGRAMMING LANGUAGE USING THE FRAMEWORK OF PATTERN DESIGN.
Prerequisites
THE COURSE REQUIRES BASIC KNOWLEDGE OF THE PYTHON PROGRAMMING LANGUAGE.
Contents
INTRODUCTION TO MACHINE LEARNING. BIAS AND VARIANCE ERRORS. OVERFITTING. THE CURSE OF DIMENSIONALITY.
(LECTURE / PRACTICE / LABORATORY HOURS: 6/0/2)

ARTIFICIAL NEURAL NETWORKS. PERCEPTRONS. MLP. Descent Gradient Optimization. Back propagation
(LECTURE / PRACTICE / LABORATORY HOURS: 4/0/4)

CLUSTERING WITH NEURAL NETWORKS. LVQ. MANIFOLD LEARNING AND SELF ORGANIZING MAPS.
(LECTURE / PRACTICE / LABORATORY HOURS: 3/0/3)

DEEP LEARNING. CONVOLUTIONAL NEURAL NETWORKS.
(LECTURE / PRACTICE / LABORATORY HOURS: 4/0/6)

Deep network training. Transfer learning
(LECTURE / PRACTICE / LABORATORY HOURS: 4/0/4)

RECURRENT NETWORKS. LSTM AND GRU
(LECTURE / PRACTICE / LABORATORY HOURS: 4/0/4)

REINFORCEMENT LEARNING. Q-LEARNING
(LECTURE / PRACTICE / LABORATORY HOURS: 4/0/4)

ADVANCED DEEP LEARNING ARCHITECTURES. AUTOENCODERS. SIMULTANEOUS DETECTION AND RECOGNITION. YOLO. GENERATIVE-ADVERSARIAL NETWORKS.
(LECTURE / PRACTICE / LABORATORY HOURS: 8/0/8)

TOTAL LECTURE / PRACTICE / LABORATORY HOURS: 37/0/35
Teaching Methods
"DEEP LEARNING", IAN GOODFELLOW AND YOSHUA BENGIO AND AARON COURVILLE, MIT PRESS.

THE TEACHING MATERIAL IS AVAILABLE ON THE UNIVERSITY E-LEARNING PLATFORM (HTTP://ELEARNING.UNISA.IT) ACCESSIBLE TO STUDENTS USING THEIR OWN UNIVERSITY CREDENTIALS.
Verification of learning
THE EXAM IS COMPOSED BY THE DISCUSSION OF A TEAM PROJECTWORK (FOR 3-4 PERSONS TEAMS) AND AN ORAL INTERVIEW. THE DISCUSSION OF THE PROJECTWORK AIMS AT EVALUATING THE ABILITY TO BUILD A SIMPLE APPLICATION OF THE TOOLS PRESENTED IN THE COURSE TO A PROBLEM ASSIGNED BY THE TEACHER, AND INCLUDES A PRACTICAL DEMONSTRATION OF THE REALIZED APPLICATION, A PRESENTATION OF A QUANTITATIVE EVALUATION OF THE APPLICATION PERFORMANCE AND A DESCRIPTION OF THE TECHNICAL CHOICES INVOLVED IN ITS REALIZATION. THE INTERVIEW EVALUATES THE LEVEL OF THE KNOWLEDGE AND UNDERSTANDING OF THE THEORETICAL TOPICS, TOGETHER WITH THE EXPOSITION ABILITY OF THE CANDIDATE.
Texts
"DEEP LEARNING", IAN GOODFELLOW AND YOSHUA BENGIO AND AARON COURVILLE, MIT PRESS.

LECTURE NOTES AND OTHER MATERIAL PROVIDED DURING THE COURSE

THE TEACHING MATERIAL WILL BE AVAILABLE ON THE UNIVERSITY E-LEARNING PLATFORM (HTTP://ELEARNING.UNISA.IT) ACCESSIBLE TO STUDENTS USING THEIR OWN UNIVERSITY CREDENTIALS.
More Information
THE COURSE IS HELD IN ENGLISH
  BETA VERSION Data source ESSE3