Giuseppe POLESE | DEEP LEARNING

cod. 0522500149

DEEP LEARNING

	0522500149
	COMPUTER SCIENCE
	EQF7
	COMPUTER SCIENCE
	2024/2025

CURRICULUM DATA SCIENCE & MACHINE LEARNING

	YEAR OF DIDACTIC SYSTEM 2016
	SPRING SEMESTER

TEACHING UNITS

SSD	CFU	HOURS	ACTIVITY	TYPE OF ACTIVITY
INF/01	4	32	LESSONS	COMPULSORY SUBJECTS, CHARACTERISTIC OF THE CLASS
INF/01	2	16	LAB	COMPULSORY SUBJECTS, CHARACTERISTIC OF THE CLASS

PROFESSORS

	GIUSEPPE POLESE T Curriculum
	LOREDANA CARUCCIO Curriculum

	Objectives
	THE STUDENT WILL ACQUIRE: •KNOWLEDGE OF THE THEORETICAL PRINCIPLES AND BASIC ALGORITHMS OF DEEP LEARNING, WITH PARTICULAR EMPHASIS ON ARTIFICIAL NEURAL NETWORKS AND TRANSFORMER ARCHITECTURES. •FUNDAMENTAL CONCEPTS RELATED TO THE OPERATION OF ARTIFICIAL NEURAL NETWORKS AND THE DIFFERENT DEEP LEARNING PARADIGMS. •KNOWLEDGE OF THE MAIN DEEP LEARNING MODELS AND ALGORITHMS TO BE APPLIED TO MULTIMEDIA AND TEXT DATA. •EXPLAIN THE DIFFERENT LEARNING ALGORITHMS FOR NEURAL NETWORKS, INCLUDING MODELS BASED ON TRANSFORMER AND GRAPH ARCHITECTURES. THE STUDENT WILL BE ABLE TO: •ANALYZE REAL-WORLD PROBLEMS AND CHOOSE THE MOST APPROPRIATE DEEP LEARNING TECHNIQUES FOR SOLVING THEM, WHILE ALSO DEVELOPING THE ABILITY TO IMPLEMENT THEM. •APPLY DEEP LEARNING MODELS TO REAL-WORLD PROBLEMS IN VARIOUS DOMAINS, SUCH AS COMPUTER VISION, NATURAL LANGUAGE PROCESSING, ROBOTICS, AND BIOINFORMATICS. •DESIGN, IMPLEMENT, AND TRAIN DEEP LEARNING MODELS USING POPULAR SOFTWARE LIBRARIES AND FRAMEWORKS. •EVALUATE THE PERFORMANCE OF DEEP LEARNING MODELS AND OPTIMIZE THEIR PERFORMANCE. •QUICKLY FAMILIARIZE THEMSELVES WITH NEW DEEP LEARNING TOPICS AND INTERACT WITH COMMUNITIES OF DEVELOPERS AND EXPERTS IN THIS AREA. THE STUDENT WILL GAIN INDEPENDENCE OF JUDGMENT AS THEY WILL BE ABLE TO: •STUDY THEORETICAL CONCEPTS AND APPLY THEM IN VARIOUS APPLICATION DOMAINS THROUGH THE RESOLUTION OF EXERCISES THAT ALLOW THEM TO ASSESS THE LEVEL OF UNDERSTANDING ACHIEVED AND POSSIBLY INCREASE IT. •EVALUATE THE APPROPRIATE DEEP LEARNING ARCHITECTURE AND MODEL TO USE FOR SPECIFIC PROBLEMS OF DIFFERENT NATURE. •EVALUATE SUITABLE DATA SOURCES TO ADDRESS REAL-WORLD PROBLEMS WITH DEEP LEARNING MODELS. •ASSESS THE GOODNESS OF DEEP LEARNING METHODOLOGIES AND THE CORRECTNESS OF THE RESULTS OBTAINED BY DEEP LEARNING MODELS AND DRAW SIGNIFICANT CONCLUSIONS. THE STUDENT WILL BE ABLE TO: •EFFECTIVELY COMMUNICATE DEEP LEARNING CONCEPTS TO BOTH EXPERT AND NON-EXPERT AUDIENCES. •DESCRIBE, THROUGH APPROPRIATE PROJECT DOCUMENTATION, THE DESIGN CHOICES MADE DURING THE DESIGN AND DEVELOPMENT PHASES, ARGUING AND MOTIVATING THEM. •EFFECTIVELY PRESENT THE SCIENTIFIC RESULTS OBTAINED FROM THE APPLICATION OF DEEP LEARNING MODELS TO SPECIFIC PROBLEMS IN ACADEMIC AND PROFESSIONAL CONTEXTS. •COLLABORATE EFFECTIVELY WITH OTHER PROFESSIONALS TO DEVELOP AND IMPLEMENT DEEP LEARNING-BASED SOLUTIONS. THE STUDENT WILL BE ABLE TO: •DEVELOP SKILLS IN STUDYING THE CHARACTERISTICS OF DIFFERENT DEEP LEARNING MODELS, LEARNING TO COMPARE THEM CRITICALLY AND IDENTIFY THE MOST SUITABLE ONES FOR A GIVEN PROBLEM. •ACQUIRE THE ABILITY TO EVALUATE THE PERFORMANCE OF DEEP LEARNING MODELS AND IDENTIFY THE TUNING ACTIVITIES NECESSARY FOR THEIR IMPROVEMENT. •LEARN INDEPENDENTLY THE LATEST DEEP LEARNING CONCEPTS AND TECHNIQUES.

THE STUDENT WILL ACQUIRE:
•KNOWLEDGE OF THE THEORETICAL PRINCIPLES AND BASIC ALGORITHMS OF DEEP LEARNING, WITH PARTICULAR EMPHASIS ON ARTIFICIAL NEURAL NETWORKS AND TRANSFORMER ARCHITECTURES.
•FUNDAMENTAL CONCEPTS RELATED TO THE OPERATION OF ARTIFICIAL NEURAL NETWORKS AND THE DIFFERENT DEEP LEARNING PARADIGMS.
•KNOWLEDGE OF THE MAIN DEEP LEARNING MODELS AND ALGORITHMS TO BE APPLIED TO MULTIMEDIA AND TEXT DATA.
•EXPLAIN THE DIFFERENT LEARNING ALGORITHMS FOR NEURAL NETWORKS, INCLUDING MODELS BASED ON TRANSFORMER AND GRAPH ARCHITECTURES.
THE STUDENT WILL BE ABLE TO:
•ANALYZE REAL-WORLD PROBLEMS AND CHOOSE THE MOST APPROPRIATE DEEP LEARNING TECHNIQUES FOR SOLVING THEM, WHILE ALSO DEVELOPING THE ABILITY TO IMPLEMENT THEM.
•APPLY DEEP LEARNING MODELS TO REAL-WORLD PROBLEMS IN VARIOUS DOMAINS, SUCH AS COMPUTER VISION, NATURAL LANGUAGE PROCESSING, ROBOTICS, AND BIOINFORMATICS.
•DESIGN, IMPLEMENT, AND TRAIN DEEP LEARNING MODELS USING POPULAR SOFTWARE LIBRARIES AND FRAMEWORKS.
•EVALUATE THE PERFORMANCE OF DEEP LEARNING MODELS AND OPTIMIZE THEIR PERFORMANCE.
•QUICKLY FAMILIARIZE THEMSELVES WITH NEW DEEP LEARNING TOPICS AND INTERACT WITH COMMUNITIES OF DEVELOPERS AND EXPERTS IN THIS AREA.
THE STUDENT WILL GAIN INDEPENDENCE OF JUDGMENT AS THEY WILL BE ABLE TO:
•STUDY THEORETICAL CONCEPTS AND APPLY THEM IN VARIOUS APPLICATION DOMAINS THROUGH THE RESOLUTION OF EXERCISES THAT ALLOW THEM TO ASSESS THE LEVEL OF UNDERSTANDING ACHIEVED AND POSSIBLY INCREASE IT.
•EVALUATE THE APPROPRIATE DEEP LEARNING ARCHITECTURE AND MODEL TO USE FOR SPECIFIC PROBLEMS OF DIFFERENT NATURE.
•EVALUATE SUITABLE DATA SOURCES TO ADDRESS REAL-WORLD PROBLEMS WITH DEEP LEARNING MODELS.
•ASSESS THE GOODNESS OF DEEP LEARNING METHODOLOGIES AND THE CORRECTNESS OF THE RESULTS OBTAINED BY DEEP LEARNING MODELS AND DRAW SIGNIFICANT CONCLUSIONS.
THE STUDENT WILL BE ABLE TO:
•EFFECTIVELY COMMUNICATE DEEP LEARNING CONCEPTS TO BOTH EXPERT AND NON-EXPERT AUDIENCES.
•DESCRIBE, THROUGH APPROPRIATE PROJECT DOCUMENTATION, THE DESIGN CHOICES MADE DURING THE DESIGN AND DEVELOPMENT PHASES, ARGUING AND MOTIVATING THEM.
•EFFECTIVELY PRESENT THE SCIENTIFIC RESULTS OBTAINED FROM THE APPLICATION OF DEEP LEARNING MODELS TO SPECIFIC PROBLEMS IN ACADEMIC AND PROFESSIONAL CONTEXTS.
•COLLABORATE EFFECTIVELY WITH OTHER PROFESSIONALS TO DEVELOP AND IMPLEMENT DEEP LEARNING-BASED SOLUTIONS.
THE STUDENT WILL BE ABLE TO:
•DEVELOP SKILLS IN STUDYING THE CHARACTERISTICS OF DIFFERENT DEEP LEARNING MODELS, LEARNING TO COMPARE THEM CRITICALLY AND IDENTIFY THE MOST SUITABLE ONES FOR A GIVEN PROBLEM.
•ACQUIRE THE ABILITY TO EVALUATE THE PERFORMANCE OF DEEP LEARNING MODELS AND IDENTIFY THE TUNING ACTIVITIES NECESSARY FOR THEIR IMPROVEMENT.
•LEARN INDEPENDENTLY THE LATEST DEEP LEARNING CONCEPTS AND TECHNIQUES.

	Prerequisites
	IT IS PREFERABLE TO HAVE TAKEN A COURSE IN ARTIFICIAL INTELLIGENCE FUNDAMENTALS, MACHINE LEARNING, OR ANY COURSE IN WHICH THE FUNDAMENTAL CONCEPTS OF MACHINE LEARNING HAVE BEEN ACQUIRED.

	Contents
	THE COURSE WILL FOCUS ON THE FOLLOWING TOPICS: •INTRODUCTION TO DEEP LEARNING MODELS AND APPLICATION SCENARIOS (2 HOURS) •FORWARD AND BACKPROPAGATION: INTRODUCTION TO NEURAL NETWORKS; FORWARD PROPAGATION; NON-LINEAR ACTIVATION FUNCTIONS; LOSS FUNCTIONS; BACKPROPAGATION ALGORITHMS; GRADIENT DESCENT AND OPTIMIZATION (4 HOURS) •OPTIMIZATION PROBLEMS: CLASSIFICATION OF OPTIMIZATION PROBLEMS; GRADIENT-BASED OPTIMIZATION METHODS; FIRST-ORDER VS. SECOND-ORDER OPTIMIZATION; HYPERPARAMETER TUNING (5 HOURS) •CONVOLUTIONAL NEURAL NETWORKS (CNNS): INTRODUCTION TO CNNS; CONVOLUTION OPERATIONS; POOLING LAYERS; CNN ARCHITECTURES; APPLICATIONS OF CNNS (4 HOURS) •INTRODUCTION TO NATURAL LANGUAGE PROCESSING (NLP); RECURRENT NEURAL NETWORKS (RNNS); GATED RECURRENT UNIT (GRU); LONG SHORT-TERM MEMORY (LSTM); SEQUENCE-TO-SEQUENCE LEARNING WITH RNNS; INTRODUCTION AND APPLICATIONS OF EMBEDDINGS (5 HOURS) •GRAPH NEURAL NETWORKS (GNNS): INTRODUCTION TO GRAPH DATA; GRAPH EMBEDDING; GRAPH CONVOLUTIONAL NETWORK (GCN) (4 HOURS) •TRANSFORMERS: TRANSFER LEARNING; ATTENTION MECHANISM; TRANSFORMER ARCHITECTURE; APPLICATIONS OF TRANSFORMERS (E.G., BERT, GPT) (4 HOURS) •ADVANCED AND COLLABORATIVE LEARNING: ACTIVE LEARNING; FEDERATED LEARNING; LEARNING FROM DATA STREAMS AND TIME SERIES (4 HOURS) LABORATORY LESSONS WILL FOCUS ON THE FOLLOWING TOPICS: •INTRODUCTION TO PYTHON (4 HOURS) •SCIKIT-LEARN (2 HOURS) •TRANSFORMER LIBRARY SUITE FOR NLP (2 HOURS) •KERAS AND TENSORFLOW (2 HOURS) •INTRODUCTION TO CUDA AND OPENCV (4 HOURS) •CASE STUDIES (2 HOURS)

Contents

THE COURSE WILL FOCUS ON THE FOLLOWING TOPICS:
•INTRODUCTION TO DEEP LEARNING MODELS AND APPLICATION SCENARIOS (2 HOURS)
•FORWARD AND BACKPROPAGATION: INTRODUCTION TO NEURAL NETWORKS; FORWARD PROPAGATION; NON-LINEAR ACTIVATION FUNCTIONS; LOSS FUNCTIONS; BACKPROPAGATION ALGORITHMS; GRADIENT DESCENT AND OPTIMIZATION (4 HOURS)
•OPTIMIZATION PROBLEMS: CLASSIFICATION OF OPTIMIZATION PROBLEMS; GRADIENT-BASED OPTIMIZATION METHODS; FIRST-ORDER VS. SECOND-ORDER OPTIMIZATION; HYPERPARAMETER TUNING (5 HOURS)
•CONVOLUTIONAL NEURAL NETWORKS (CNNS): INTRODUCTION TO CNNS; CONVOLUTION OPERATIONS; POOLING LAYERS; CNN ARCHITECTURES; APPLICATIONS OF CNNS (4 HOURS)
•INTRODUCTION TO NATURAL LANGUAGE PROCESSING (NLP); RECURRENT NEURAL NETWORKS (RNNS); GATED RECURRENT UNIT (GRU); LONG SHORT-TERM MEMORY (LSTM); SEQUENCE-TO-SEQUENCE LEARNING WITH RNNS; INTRODUCTION AND APPLICATIONS OF EMBEDDINGS (5 HOURS)
•GRAPH NEURAL NETWORKS (GNNS): INTRODUCTION TO GRAPH DATA; GRAPH EMBEDDING; GRAPH CONVOLUTIONAL NETWORK (GCN) (4 HOURS)
•TRANSFORMERS: TRANSFER LEARNING; ATTENTION MECHANISM; TRANSFORMER ARCHITECTURE; APPLICATIONS OF TRANSFORMERS (E.G., BERT, GPT) (4 HOURS)
•ADVANCED AND COLLABORATIVE LEARNING: ACTIVE LEARNING; FEDERATED LEARNING; LEARNING FROM DATA STREAMS AND TIME SERIES (4 HOURS)
LABORATORY LESSONS WILL FOCUS ON THE FOLLOWING TOPICS:
•INTRODUCTION TO PYTHON (4 HOURS)
•SCIKIT-LEARN (2 HOURS)
•TRANSFORMER LIBRARY SUITE FOR NLP (2 HOURS)
•KERAS AND TENSORFLOW (2 HOURS)
•INTRODUCTION TO CUDA AND OPENCV (4 HOURS)
•CASE STUDIES (2 HOURS)

	Teaching Methods
	THE TEACHING METHODS CONSIST OF 32 HOURS OF LECTURES INTEGRATED WITH 16 HOURS OF LABORATORY SESSIONS ON THE MAIN TOOLS AND APPLICATIONS FOR DEVELOPING DEEP LEARNING MODELS. STUDENTS ARE GUIDED TO LEARN CRITICALLY AND RESPONSIBLY EVERYTHING THAT THE PROFESSOR PRESENTS DURING THE LECTURES WITH THE AIM OF DESIGNING AND DEVELOPING DEEP LEARNING MODELS. ATTENDANCE AT LECTURES IS STRONGLY RECOMMENDED. THE TOPICS OF THE PROGRAM ARE PRESENTED WITH THE AID OF POWERPOINT PRESENTATIONS, STIMULATING CRITICAL DISCUSSIONS WITH THE CLASS. FOR EACH TOPIC COVERED, POSSIBLE TASKS ARE ILLUSTRATED THAT CAN BE THE SUBJECT OF A COURSE PROJECT BY ONE OR MORE STUDENTS. AS FOR THE APPLICATION TOOLS, IN ADDITION TO THE USE OF POWERPOINT PRESENTATIONS, IN WHICH CONCEPTS AND ANY LINKS TO FORUMS, MANUALS AND IN-DEPTH PLATFORMS ARE PRESENTED, WHICH CAN ALSO BE EXECUTED BY STUDENTS FROM THEIR OWN WORKSTATION, HAVING THE POSSIBILITY OF ASKING FOR CLARIFICATION AND RESOLVE ANY TECHNICAL PROBLEMS WITH THE PROFESSOR.

Teaching Methods

THE TEACHING METHODS CONSIST OF 32 HOURS OF LECTURES INTEGRATED WITH 16 HOURS OF LABORATORY SESSIONS ON THE MAIN TOOLS AND APPLICATIONS FOR DEVELOPING DEEP LEARNING MODELS. STUDENTS ARE GUIDED TO LEARN CRITICALLY AND RESPONSIBLY EVERYTHING THAT THE PROFESSOR PRESENTS DURING THE LECTURES WITH THE AIM OF DESIGNING AND DEVELOPING DEEP LEARNING MODELS. ATTENDANCE AT LECTURES IS STRONGLY RECOMMENDED. THE TOPICS OF THE PROGRAM ARE PRESENTED WITH THE AID OF POWERPOINT PRESENTATIONS, STIMULATING CRITICAL DISCUSSIONS WITH THE CLASS. FOR EACH TOPIC COVERED, POSSIBLE TASKS ARE ILLUSTRATED THAT CAN BE THE SUBJECT OF A COURSE PROJECT BY ONE OR MORE STUDENTS. AS FOR THE APPLICATION TOOLS, IN ADDITION TO THE USE OF POWERPOINT PRESENTATIONS, IN WHICH CONCEPTS AND ANY LINKS TO FORUMS, MANUALS AND IN-DEPTH PLATFORMS ARE PRESENTED, WHICH CAN ALSO BE EXECUTED BY STUDENTS FROM THEIR OWN WORKSTATION, HAVING THE POSSIBILITY OF ASKING FOR CLARIFICATION AND RESOLVE ANY TECHNICAL PROBLEMS WITH THE PROFESSOR.

	Verification of learning
	THE ACHIEVEMENT OF THE TEACHING OBJECTIVES IS CERTIFIED BY PASSING AN EXAM WITH AN EVALUATION OUT OF THIRTY. THE EXAM INCLUDES THE DEVELOPMENT OF A PROJECT AND AN ORAL EXAM. THE PROJECT CAN BE INDIVIDUAL OR GROUP AND IS AIMED AT ASCERTAINING THE ABILITY TO APPLY THE KNOWLEDGE ACQUIRED. IT CAN BE CARRIED OUT BY CHOOSING FROM A RANGE OF PROPOSALS MADE BY THE PROFESSOR, WITH THE POSSIBILITY OF CARRYING OUT A JOINT PROJECT WITH SOME OF THE OTHER MASTER'S DEGREE COURSES OR PARTICIPATING IN INTERNATIONAL DEEP LEARNING COMPETITIONS. DURING THE COURSE OF THE PROJECT, STUDENTS WILL HAVE TO INTERACT WITH THE COURSE PROFESSOR IN ORDER TO COMMUNICATE THE PROGRESS OF THE PROJECT AND ANY CRITICAL ISSUES THAT HAVE EMERGED, AGREEING ON THE OBJECTIVES AND METHODS OF CONTINUING THE PROJECT. AT THE END OF THE PROJECT, STUDENTS MUST SUBMIT TO THE PROFESSOR A DOCUMENT CONTAINING THE PROJECT DOCUMENTATION AND A POWERPOINT PRESENTATION OF THE PROJECT LASTING APPROXIMATELY 30 MINUTES. AFTER PRESENTING THE PROJECT, STUDENTS MUST TAKE AN INDIVIDUAL ORAL TEST. THIS TEST CONSISTS OF AN INTERVIEW WITH QUESTIONS AND DISCUSSION ON THE THEORETICAL AND METHODOLOGICAL CONTENTS COVERED IN CLASS AND IS AIMED AT ASCERTAINING THE ABILITY OF KNOWLEDGE AND UNDERSTANDING, AS WELL AS THE ABILITY TO EXPLAIN THE CONCEPTS. THE ORAL TEST CAN BE CARRIED OUT ON THE SAME DATE AS THE PRESENTATION OF THE PROJECT, OR ON ANOTHER DATE THAT THE INDIVIDUAL MEMBERS OF THE GROUP CAN AGREE WITH THE PROFESSOR. THE FINAL GRADE GENERALLY COMES FROM THE AVERAGE OF THE MARKS OUT OF THIRTY OBTAINED IN EACH OF THE TWO TESTS.

Verification of learning

THE ACHIEVEMENT OF THE TEACHING OBJECTIVES IS CERTIFIED BY PASSING AN EXAM WITH AN EVALUATION OUT OF THIRTY. THE EXAM INCLUDES THE DEVELOPMENT OF A PROJECT AND AN ORAL EXAM. THE PROJECT CAN BE INDIVIDUAL OR GROUP AND IS AIMED AT ASCERTAINING THE ABILITY TO APPLY THE KNOWLEDGE ACQUIRED. IT CAN BE CARRIED OUT BY CHOOSING FROM A RANGE OF PROPOSALS MADE BY THE PROFESSOR, WITH THE POSSIBILITY OF CARRYING OUT A JOINT PROJECT WITH SOME OF THE OTHER MASTER'S DEGREE COURSES OR PARTICIPATING IN INTERNATIONAL DEEP LEARNING COMPETITIONS. DURING THE COURSE OF THE PROJECT, STUDENTS WILL HAVE TO INTERACT WITH THE COURSE PROFESSOR IN ORDER TO COMMUNICATE THE PROGRESS OF THE PROJECT AND ANY CRITICAL ISSUES THAT HAVE EMERGED, AGREEING ON THE OBJECTIVES AND METHODS OF CONTINUING THE PROJECT. AT THE END OF THE PROJECT, STUDENTS MUST SUBMIT TO THE PROFESSOR A DOCUMENT CONTAINING THE PROJECT DOCUMENTATION AND A POWERPOINT PRESENTATION OF THE PROJECT LASTING APPROXIMATELY 30 MINUTES. AFTER PRESENTING THE PROJECT, STUDENTS MUST TAKE AN INDIVIDUAL ORAL TEST. THIS TEST CONSISTS OF AN INTERVIEW WITH QUESTIONS AND DISCUSSION ON THE THEORETICAL AND METHODOLOGICAL CONTENTS COVERED IN CLASS AND IS AIMED AT ASCERTAINING THE ABILITY OF KNOWLEDGE AND UNDERSTANDING, AS WELL AS THE ABILITY TO EXPLAIN THE CONCEPTS. THE ORAL TEST CAN BE CARRIED OUT ON THE SAME DATE AS THE PRESENTATION OF THE PROJECT, OR ON ANOTHER DATE THAT THE INDIVIDUAL MEMBERS OF THE GROUP CAN AGREE WITH THE PROFESSOR. THE FINAL GRADE GENERALLY COMES FROM THE AVERAGE OF THE MARKS OUT OF THIRTY OBTAINED IN EACH OF THE TWO TESTS.

	Texts
	•I. DRORI (2022) “THE SCIENCE OF DEEP LEARNING”, CAMBRIDGE UNIVERSITY PRESS •C. M. BISHOP (2024) “DEEP LEARNING FOUNDATIONS AND CONCEPTS”, SPRINGER •A. GERON (2019) “HANDS-ON MACHINE LEARNING WITH SCIKIT-LEARN, KERAS, AND TENSORFLOW: CONCEPTS, TOOLS, AND TECHNIQUES TO BUILD INTELLIGENT SYSTEMS”, O REILLY MEDIA •P. DEITEL, H. DEITEL (2021) INTRODUZIONE A PYTHON – PER L’INFORMATICA E LA DATA SCIENCE, PEARSON.

Texts

•I. DRORI (2022) “THE SCIENCE OF DEEP LEARNING”, CAMBRIDGE UNIVERSITY PRESS
•C. M. BISHOP (2024) “DEEP LEARNING FOUNDATIONS AND CONCEPTS”, SPRINGER
•A. GERON (2019) “HANDS-ON MACHINE LEARNING WITH SCIKIT-LEARN, KERAS, AND TENSORFLOW: CONCEPTS, TOOLS, AND TECHNIQUES TO BUILD INTELLIGENT SYSTEMS”, O REILLY MEDIA
•P. DEITEL, H. DEITEL (2021) INTRODUZIONE A PYTHON – PER L’INFORMATICA E LA DATA SCIENCE, PEARSON.

	More Information
	ATTENDANCE OF THE COURSE IS STRONGLY RECOMMENDED. STUDENTS MUST BE PREPARED TO SPEND A REASONABLE AMOUNT OF TIME STUDYING OUTSIDE OF CLASS. SATISFACTORY PREPARATION REQUIRES ON AVERAGE 1 HOUR OF STUDY FOR EACH HOUR SPENT IN THE CLASSROOM AND APPROXIMATELY 80 HOURS FOR THE DEVELOPMENT OF THE PROJECT. THE LESSON MATERIAL WILL BE AVAILABLE ON THE DEPARTMENTAL E-LEARNING PLATFORM HTTP://ELEARNING.INFORMATICA.UNISA.IT/EL-PLATFORM/

More Information

ATTENDANCE OF THE COURSE IS STRONGLY RECOMMENDED. STUDENTS MUST BE PREPARED TO SPEND A REASONABLE AMOUNT OF TIME STUDYING OUTSIDE OF CLASS. SATISFACTORY PREPARATION REQUIRES ON AVERAGE 1 HOUR OF STUDY FOR EACH HOUR SPENT IN THE CLASSROOM AND APPROXIMATELY 80 HOURS FOR THE DEVELOPMENT OF THE PROJECT. THE LESSON MATERIAL WILL BE AVAILABLE ON THE DEPARTMENTAL E-LEARNING PLATFORM HTTP://ELEARNING.INFORMATICA.UNISA.IT/EL-PLATFORM/

BETA VERSION Data source ESSE3 [Ultima Sincronizzazione: 2024-11-18]

Giuseppe POLESE | DEEP LEARNING