Stefania TOMASIELLO | INTRODUCTION TO MACHINE LEARNING
Stefania TOMASIELLO INTRODUCTION TO MACHINE LEARNING
cod. 0612400061
INTRODUCTION TO MACHINE LEARNING
| 0612400061 | |
| DEPARTMENT OF INDUSTRIAL ENGINEERING | |
| EQF6 | |
| ELECTRONIC ENGINEERING | |
| 2024/2025 |
| OBBLIGATORIO | |
| YEAR OF COURSE 1 | |
| YEAR OF DIDACTIC SYSTEM 2018 | |
| SPRING SEMESTER |
| SSD | CFU | HOURS | ACTIVITY | |
|---|---|---|---|---|
| NN | 3 | 45 | LESSONS |
| Objectives | |
|---|---|
| THE EDUCATIONAL GOALS OF THE COURSE CAN BE SUMMARIZED AS FOLLOWS: - INTRODUCTION TO MACHINE LEARNING (ML); - INTRODUCTION TO THE PYTHON LANGUAGE AND ML WITH PYTHON. KNOWLEDGE AND COMPREHENSION SKILLS: AT THE END OF THE TEACHING ACTIVITIES, THE STUDENTS WILL BE ABLE TO UNDERSTAND THE MAIN ML TECHNIQUES. IN PARTICULAR, THEY WILL BE ABLE TO PICK THE PROPER APPROACHES FOR SOLVING REAL PROBLEMS. THE STUDENTS WILL ACQUIRE SKILLS RELATED TO THE USE OF THE PYTHON PROGRAMMING LANGUAGE, ESPECIALLY IN THE ML CONTEXT. APPLIED KNOWLEDGE AND COMPREHENSION SKILLS: AT THE END OF THE COURSE, THE STUDENTS WILL BE ABLE TO TACKLE REGRESSION, CLASSIFICATION AND CLUSTERING PROBLEMS USING APPROPRIATE ML TECHNIQUES. AUTONOMY OF JUDGMENT: STUDENTS WILL BE ABLE TO IDENTIFY THE MOST APPROPRIATE APPROACHES TO OBTAIN THE BEST SOLUTION FOR SOLVING A GIVEN PROBLEM. COMMUNICATION SKILLS: AT THE END OF THE COURSE, THE STUDENTS WILL ACQUIRE THE BASIC TERMINOLOGY AND VOCABULARY OF ML. BESIDES, THE STUDENTS WILL BE ABLE TO REPRESENT THE TYPICAL COMPUTATIONAL SCHEMES IN THE ML CONTEXT THROUGH APPROPRIATE GRAPHICAL FORMALISMS. LEARNING SKILLS: THE COURSE AIMS TO DEVELOP STUDENTS' LEARNING SKILLS SO THAT THEY WILL BE ABLE TO UPDATE THEIR KNOWLEDGE AND SKILLS INDEPENDENTLY. STUDENTS SHOULD BE ABLE TO APPLY THE ACQUIRED KNOWLEDGE TO UNEXPLORED CONTEXTS AND DEEPEN THE TOPICS COVERED USING MATERIAL AND LIBRARIES DIFFERENT FROM THOSE PROPOSED. |
| Prerequisites | |
|---|---|
| PREREQUISITE: - FUNDAMENTALS OF COMPUTER SCIENCE |
| Contents | |
|---|---|
| BASIC CONCEPTS (6 HOURS) INTRODUCTION TO NEURAL NETWORKS. REGRESSION, CLASSIFICATION AND CLUSTERING PROBLEMS. PRACTICE SESSIONS PROGRAMMING LANGUAGE: PYTHON. |
| Teaching Methods | |
|---|---|
| TEACHING METHODS THERE ARE LECTURES AND PRACTICE SESSIONS. DURING THE PRACTICE SESSIONS, STUDENTS ARE ASKED TO TACKLE A PROBLEM USING THE TECHNIQUES PRESENTED DURING THE LECTURES. THE PROCESS IS GUIDED BY THE LECTURER, AND IT AIMS TO DEVELOP AND STRENGTHEN THE STUDENTS' ABILITY TO IDENTIFY THE MOST SUITABLE METHODS FOR THE APPLICATION. |
| Verification of learning | |
|---|---|
| ASSESSMENT METHODS THE FINAL ASSIGNMENT IS A PROJECT RELATED TO THE COURSE TOPICS. THE EFFECTIVENESS OF THE ADOPTED METHODS AND THE PRESENTATION STYLE WILL BE EVALUATED. THE FINAL GRADE IS PASS OR FAIL. TO PASS 51 POINTS: NOTEBOOKS FROM THE PRACTICE SESSIONS (UP TO 10 POINTS), PROJECT WORK (UP TO 45 POINTS). |
| Texts | |
|---|---|
| SUGGESTED TEXTBOOKS - A. ZOLLANVARI, MACHINE LEARNING WITH PYTHON, SPRINGER (2023) - T. T. TEOH, Z. RONG, ARTIFICIAL INTELLIGENCE WITH PYTHON, SPRINGER (2022) STUDY MATERIAL (LECTURE SLIDES, CODES) IN MOODLE. |
| More Information | |
|---|---|
| THE LANGUAGE IS ITALIAN. STUDY MATERIAL IN ENGLISH. |
BETA VERSION Data source ESSE3 [Ultima Sincronizzazione: 2024-11-18]
