Vai al contenuto principale
Oggetto:
Oggetto:

Machine Learning

Oggetto:

Machine Learning

Oggetto:

Anno accademico 2020/2021

Codice dell'attività didattica
FIS0125
Docente
Prof. Piero Fariselli (Titolare del corso)
Corso di studi
Laurea Magistrale Interateneo in Fisica dei sistemi complessi
Anno
1° anno 2° anno
Periodo didattico
Terzo periodo didattico
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. Conoscenza di 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. 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. Lo studente sarà in grado di sviluppare pacchetti propri utilizzando librerie standard.

The objective of the course is to introduce algorithms and machine learning models for cross-disciplinary applications. 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, the students are expected to be able to write their packages using standard libraries.

Oggetto:

Risultati dell'apprendimento attesi

Compresione dei fondamenti teorici deli modelli di machine learning presentati e essere in grado di svilupparne dei nuovi.  Conoscenza di alcune librerie Python per il machine learning e loro utilizzo.

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. The students acquire expertise using some Python libraries.

Oggetto:

Modalità di insegnamento

Lezioni alla lavagna e con diapositive, ed esercizi al computer.

Nel caso le problematiche relative al COVID-19 permanessero, 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.

In case the problem with COVID19 remains, the lectures will be provided as webex and they will be registered (the links will be available on moodle).

If the COVID19 problem persits

Oggetto:

Modalità di verifica dell'apprendimento

Discussione alla lavagna, assegnazione e valutazione di semplici progetti di programmazione.

Nel caso le problematiche relative al COVID-19 permanessero, verranno valutati i progetti in python distribuiti durante il corso e discussi in via telematica.

Discussion at the blackboard and assignment of programming projects.

In case the problem with COVID19 remains, the evaluation will be performed on the Python notebook provided during the course and discussed through Webex calls.

Oggetto:

Attività di supporto

Oggetto:

Programma

  • Introduction to machine learning: relation with statistical learning, types of learning (supervised, unsupervised, reinforcement learning, collaborative filtering).
  • Introduction to simple predictive models: regression and classification.
  • A quick review of Python language.
  • 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.
  • Introduction to ensemble learning (bagging and boosting), multitask learning and multi-instance learning.
  • Elements of biological-inspired computations for optimization: genetic algorithms, ant colony optimization
  • The concept and examples of Reinforcement Learning.

  • Introduction to machine learning: relation with statistical learning, types of learning (supervised, unsupervised, reinforcement learning, collaborative filtering).
  • Introduction to simple predictive models: regression and classification.
  • A quick review of Python language.
  • 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.
  • Introduction to ensemble learning (bagging and boosting), multitask learning and multi-instance learning.
  • Elements of biological-inspired computations for optimization: genetic algorithms, ant colony optimization
  • The concept and examples of Reinforcement Learning.

Testi consigliati e bibliografia

Oggetto:

  • Mehta et al. A high-bias, low-variance introduction to Machine Learning for physicists. 2019. Phys Rep. 810:1-124 https://arxiv.org/abs/1803.08823
  • C.M. Bishop. Pattern Recognition and Machine Learning. Springer, 2006.
  • Francois Chollet Deep Learning with Python Manning Pubns Co, 2017
  • K.P. Machine Learning. A Probabilistic Perspective. MIT Press, 2012.
  • D. Simon. EVOLUTIONARY OPTIMIZATION ALGORITHMS. John Wiley & Sons, 2013.
  • 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

  • Mehta et al. A high-bias, low-variance introduction to Machine Learning for physicists. 2019. Phys Rep. 810:1-124 https://arxiv.org/abs/1803.08823
  • C.M. Bishop. Pattern Recognition and Machine Learning. Springer, 2006.
  • Francois Chollet Deep Learning with Python Manning Pubns Co, 2017
  • K.P. Machine Learning. A Probabilistic Perspective. MIT Press, 2012.
  • D. Simon. EVOLUTIONARY OPTIMIZATION ALGORITHMS. John Wiley & Sons, 2013.
  • 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


Oggetto:

Orario lezioni

GiorniOreAula
Martedì9:00 - 11:00
Mercoledì9:00 - 11:00
Giovedì9:00 - 11:00

Lezioni: dal 19/04/2021 al 17/06/2021

Oggetto:

Note

Oggetto:
Last update: 20/04/2021 17:51
Location: https://fisica-sc.campusnet.unito.it/robots.html
Non cliccare qui!