CODE 106788 ACADEMIC YEAR 2023/2024 CREDITS 5 cfu anno 1 INGEGNERIA ELETTRONICA 8732 (LM-29) - GENOVA 5 cfu anno INGEGNERIA ELETTRONICA 8732 (LM-29) - GENOVA SCIENTIFIC DISCIPLINARY SECTOR ING-INF/01 LANGUAGE Italian (English on demand) TEACHING LOCATION GENOVA SEMESTER 2° Semester MODULES Questo insegnamento è un modulo di: APPLIED MATHEMATICAL MODELLING AND MACHINE LEARNING TEACHING MATERIALS AULAWEB AIMS AND CONTENT LEARNING OUTCOMES The aim of the course is to provide the basis for the design and development of classification and regression software algorithms. The student is introduced to different concepts of machine learning (linear models, decision trees, ensemble learning, artificial neural networks, etc.) and supported through extensive exercises during lectures exploiting several software library in Python (NumPy, Pandas, SciKitLearn e TensorFlow). The last part of the course will be focused on the model deployment on embedded systems. AIMS AND LEARNING OUTCOMES The aim of the course is to provide the basis for the design and development of classification and regression software algorithms. The student is introduced to different concepts of machine learning (linear models, decision trees, ensemble learning, artificial neural networks, etc.) and supported through extensive exercises during lectures exploiting several software library in Python (NumPy, Pandas, SciKitLearn e TensorFlow). The last part of the course will be focused on the model deployment on embedded systems. TEACHING METHODS The course is composed of a set of frontal lessons and a set of practice sessions. During the frontal lesson, the teacher presents the topics providing also examples of live code that are tested on a Jupyter notebook. Students can use their own laptops during the lecture in order to reproduce what is proposed by the teacher. During the practice sessions, the students have to face up with real problems that they should solve by applying the techniques learnied during the lectures. SYLLABUS/CONTENT Part 1 - Fundamental algorithms and techniques Introduction Regression Classification Linear Models Decision trees Ensemble Learning Dimensionality Reduction Unsupervised algorithms Part 2 - Neural Networks Perceptron MLP Backpropagation Convolutional networks Advanced Vision Part 3 - Deployment on embedded devices Inference Quantization TensorFlow Lite and TensorFlow Micro Deployment on NVidia Jetson platform TinyML RECOMMENDED READING/BIBLIOGRAPHY Hands-on Machine Learning with Scikit-Learn, Keras and TensorFlow Papers with Code The Elements of Statistical Learning Data Science from Scratch Neural Networks for Machine Learning TEACHERS AND EXAM BOARD RICCARDO BERTA Ricevimento: Appointments. Writing to riccardo.berta@unige.it EDOARDO RAGUSA Exam Board ALBERTO OLIVERI (President) RICCARDO BERTA (President Substitute) EDOARDO RAGUSA (President Substitute) LESSONS LESSONS START https://corsi.unige.it/8732/p/studenti-orario Class schedule The timetable for this course is available here: Portale EasyAcademy EXAMS EXAM DESCRIPTION The exam is an oral examination on the theoretical topics covered during lectures. In particular, the student has to provide fluency in the description of the main concepts of machine learning. ASSESSMENT METHODS During the oral exam, the teacher asks the student to illustrate some concepts learned in class. For each concept, the student has to present the definition, the conditions of applicability and pros/cons in relation to other approaches. During the examination, the teacher verifies that the concepts have been learned at a level of knowledge that allows the student to apply them in real cases. Exam schedule Data appello Orario Luogo Degree type Note 12/01/2024 09:00 GENOVA Orale 30/01/2024 09:00 GENOVA Orale 16/02/2024 09:00 GENOVA Orale 05/06/2024 09:00 GENOVA Orale 28/06/2024 09:00 GENOVA Orale 17/07/2024 09:00 GENOVA Orale 05/09/2024 09:00 GENOVA Orale