Vai al contenuto principale
Oggetto:
Oggetto:

Machine Learning

Oggetto:

Machine Learning

Oggetto:

Anno accademico 2022/2023

Codice dell'attività didattica
FIS0125
Docente
Piero Fariselli (Titolare del corso)
Corso di studi
Laurea Magistrale Interateneo in Fisica dei sistemi complessi
Anno
1° anno 2° anno
Periodo didattico
Primo Semestre
Tipologia
D=A scelta dello studente
Crediti/Valenza
6
SSD dell'attività didattica
FIS/07 - fisica applicata (a beni culturali, ambientali, biologia e medicina)
Modalità di erogazione
Tradizionale
Lingua di insegnamento
Inglese
Modalità di frequenza
Facoltativa
Tipologia d'esame
Orale
Prerequisiti
Analisi matematica, algebra lineare, elementi di statistica e probabilità. Programmazione in Python.
Oggetto:

Sommario insegnamento

Oggetto:

Obiettivi formativi

Il corso ha lo scopo di introdurre e appofondire algoritmi e modelli di apprendimento automatico (Machine Learning) per applicazioni interdisciplinari. Ci si aspetta che lo studente abbia le conoscenze di base di python e machine learning come quelle fornite dal corso di data mining. Il corso si prefigge di fornire allo studente la capacità di utilizzare e sviluppare strumenti di machine-learning per l'analisi dei dati, con particolare riferimento ai modelli predittivi. Le lezioni teoriche si alterneranno ad esempi di codice.

The objective of the course is to introduce algorithms and machine learning models for cross-disciplinary applications. The students are expected to have a background of python and machine learning as the foundations provided by the Data Mining course. This is an advanced course.

The students will be able to analyze and model the data with particular emphasis on the predictive models. The theoretical lectures include example fo programming codes. At the end of the course,

Oggetto:

Risultati dell'apprendimento attesi

Compresione dei fondamenti teorici deli modelli di machine learning presentati e essere in grado di svilupparne dei nuovi. 

The students are expected to possess appropriate knowledge of the theoretical aspects of the presented machine learning models and being able to design new ones.

Oggetto:

Modalità di insegnamento

Lezioni con proiezioni di diapositive, uso di lavagna ed esercizi al computer.

Le lezioni saranno solo in presenza.

Nel caso le problematiche relative al COVID-19 divenissere più serie, le lezioni si terranno in maniera sincrona con registrazione delle lezione (materiale su moodle).

 

Lectures at the blackboard, slide projection and practical exercises with a computer.

The lectures are in presence.

If the issues related to COVID-19 become more serious, the lessons will be held synchronously with recording of the lessons (material on moodle).

 

Oggetto:

Modalità di verifica dell'apprendimento

Durante il corso, verranno svolte discussioni alla lavagna, assegnazione di semplici progetti di programmazione.

Esame: la studentessa/ lo studente dovrà scegliere un lavoro di machine learning, spiegarne la parte teorica e il codice allegato (ad esempio scelto tra quelli di https://paperswithcode.com/) . Dopo la presentazione vi saranno domande generali sul corso. 

Discussion at the blackboard and assignment of programming projects, are proposed during the course.

Exam: the student has to select a paper (eg. from https://paperswithcode.com/) and he/she has to explain the theoretical bases and the python code. Then some more questions will be asked on the main course points.

Oggetto:

Attività di supporto

Oggetto:

Programma

  • Review of machine learning: relation with statistical learning, types of learning (supervised, unsupervised, reinforcement learning, collaborative filtering)
  • Introduction to probabilistic models and learning algorithms: Markov models, hidden Markov models, maximum entropy models, conditional random fields. Graphical models as unifying picture.
  • Introduction to causality.
  • Introduction to Neural Networks: feedforward, convolutional, recurrent, attention layers, transformers, ODE-NN
  • Introduction to decision trees and ensemble learning (bagging and boosting)
  • Concepts of multitask learning and multi-instance learning.
  • Survival analysis and machine learning
  • Foundations of interpretable explainable AI, local/global methods, intrisically interpretable, agnostic methods (DPD, ICE, ALE, LIME, SHAP)
  • Introduction to Deep Reinforcement Learning
  • If time allows:
    • Federated Learning
    • Elements of Quantum Machine Learning
    • Elements of biological-inspired computations for optimization: genetic algorithms, ant colony optimization

  • Review of machine learning: relation with statistical learning, types of learning (supervised, unsupervised, reinforcement learning, collaborative filtering)
  • Introduction to probabilistic models and learning algorithms: Markov models, hidden Markov models, maximum entropy models, conditional random fields. Graphical models as unifying picture.
  • Introduction to causality.
  • Introduction to Neural Networks: feedforward, convolutional, recurrent, attention layers, transformers, ODE-NN
  • Introduction to decision trees and ensemble learning (bagging and boosting)
  • Concepts of multitask learning and multi-instance learning.
  • Survival analysis and machine learning
  • Foundations of interpretable explainable AI, local/global methods, intrisically interpretable, agnostic methods (DPD, ICE, ALE, LIME, SHAP)
  • Introduction to Deep Reinforcement Learning
  • If time allows:
    • Federated Learning
    • Elements of Quantum Machine Learning
    • Elements of biological-inspired computations for optimization: genetic algorithms, ant colony optimization

Testi consigliati e bibliografia

Oggetto:

  • C.M. Bishop. Pattern Recognition and Machine Learning. Springer, 2006.
  • Vasilev Ivan, Advanced Deep Learning with Python: Design and implement advanced next-generation AI solutions using TensorFlow and PyTorch, Packt Publishing (12 dicembre 2019)
  • K.P. Machine Learning. A Probabilistic Perspective. MIT Press, 2012.
  • T. Hastie, R. Tibshirani, and J. Friedman. The Elements of Statistical Learning. Data Mining, Inference, and Prediction. 2nd edition. Springer, 2009.
  • I. Goodfellow, Y. Bengio, A. Courville. Deep Learning. MIT Press, 2016.
    R.S. Sutton and A.G. Barto. Reinforcement Learnin. An Introduction. MIT Press, 2017.
  • Andrew NG. Machine Learning Yearning: Technical Strategy for AI Engineers, In the Era of Deep Learning. deeplearning.ai, 2018
  • Christoph Molnar, Interpretable Machine Learning, Independently published (28 febbraio 2022)
  • D. Simon. EVOLUTIONARY OPTIMIZATION ALGORITHMS. John Wiley & Sons, 2013.
  • Plaat A. Deep Reinforcement Learning, pringer Verlag, Singapore; 1st ed. 2022
  • Maria Schuld e Francesco Petruccione, Machine Learning with Quantum Computers, Springer Nature; 2° edizione (18 ottobre 2021)

  • C.M. Bishop. Pattern Recognition and Machine Learning. Springer, 2006.
  • Vasilev Ivan, Advanced Deep Learning with Python: Design and implement advanced next-generation AI solutions using TensorFlow and PyTorch, Packt Publishing (12 dicembre 2019)
  • K.P. Machine Learning. A Probabilistic Perspective. MIT Press, 2012.
  • T. Hastie, R. Tibshirani, and J. Friedman. The Elements of Statistical Learning. Data Mining, Inference, and Prediction. 2nd edition. Springer, 2009.
  • I. Goodfellow, Y. Bengio, A. Courville. Deep Learning. MIT Press, 2016.
    R.S. Sutton and A.G. Barto. Reinforcement Learnin. An Introduction. MIT Press, 2017.
  • Andrew NG. Machine Learning Yearning: Technical Strategy for AI Engineers, In the Era of Deep Learning. deeplearning.ai, 2018
  • Christoph Molnar, Interpretable Machine Learning, Independently published (28 febbraio 2022)
  • D. Simon. EVOLUTIONARY OPTIMIZATION ALGORITHMS. John Wiley & Sons, 2013.
  • Plaat A. Deep Reinforcement Learning, pringer Verlag, Singapore; 1st ed. 2022
  • Maria Schuld e Francesco Petruccione, Machine Learning with Quantum Computers, Springer Nature; 2° edizione (18 ottobre 2021)


Oggetto:

Orario lezioni

GiorniOreAula
Martedì9:00 - 11:00Aula Wick Dipartimento di Fisica
Mercoledì14:00 - 16:00Sala Franzinetti Dipartimento di Fisica

Lezioni: dal 27/09/2022 al 13/01/2023

Oggetto:

Note

Questo corse prevede che lo studente sappia programmare in Python ed abbia conoscenze di base di mchine learning.

 

The course assumes that the students are fluent in Python and basic knowledge of machine learning

 

Oggetto:
Ultimo aggiornamento: 06/09/2022 12:05
Location: https://fisica-sc.campusnet.unito.it/robots.html
Non cliccare qui!