Servizi per la didattica
PORTALE DELLA DIDATTICA

Machine learning for pattern recognition

01SCSIU

A.A. 2018/19

Course Language

Inglese

Course degree

Doctorate Research in Ingegneria Informatica E Dei Sistemi - Torino

Course structure
Teaching Hours
Lezioni 20
Teachers
Teacher Status SSD h.Les h.Ex h.Lab h.Tut Years teaching
Laface Pietro     6 0 0 0 2
Teaching assistant
Espandi

Context
SSD CFU Activities Area context
*** N/A ***    
2018/19
PERIOD: MARCH This course gives a broad yet rigorous introduction to machine learning and statistical pattern recognition. It focuses on supervised generative and discriminative learning models, analyzing some important topics such as model architectures, training and evaluation techniques. The course will compare different models and classification approaches on the popular MNIST digit recognition dataset. It will also discuss about the applications of the proposed machine learning approaches to image, speech, and speaker recognition. Students will be asked to apply the acquired knowledge to develop their own classification system using labeled training and evaluation data provided during the course. Each system will then be evaluated on another unlabeled and previously unseen data set. This course belongs to an educational path on Data Science. The path is composed by - an introductory course (Data Mining: Concepts and Algorithms), covering data analytics fundamentals, which is a cultural prerequisite for the other courses - 5 thematic courses dealing in depth with specific Data Science topics, such as different algorithm types or application domains: - Data Analytics for Science and Society - Machine Learning for Pattern Recognition - Mimetic Learning - Text Mining and Analytics - Visualization and Visual Analytics
PERIOD: MARCH This course gives a broad yet rigorous introduction to machine learning and statistical pattern recognition. It focuses on supervised generative and discriminative learning models, analyzing some important topics such as model architectures, training and evaluation techniques. The course will compare different models and classification approaches on the popular MNIST digit recognition dataset. It will also discuss about the applications of the proposed machine learning approaches to image, speech, and speaker recognition. Students will be asked to apply the acquired knowledge to develop their own classification system using labeled training and evaluation data provided during the course. Each system will then be evaluated on another unlabeled and previously unseen data set. This course belongs to an educational path on Data Science. The path is composed by - an introductory course (Data Mining: Concepts and Algorithms), covering data analytics fundamentals, which is a cultural prerequisite for the other courses - 5 thematic courses dealing in depth with specific Data Science topics, such as different algorithm types or application domains: - Data Analytics for Science and Society - Machine Learning for Pattern Recognition - Mimetic Learning - Text Mining and Analytics - Visualization and Visual Analytics
- Introduction to pattern classification - Decision theory - Classification model taxonomy - Generative probabilistic models - Discriminative probabilistic models - Decision functions - Model Evaluation - Binary classification - Accuracy measures - ROC / DET curves - Multiclass classification - Generative probabilistic models - Gaussian models - Gaussian mixture models - Expectation-Maximization for GMMs - Time-dependent models: Hidden Markov Models - Inference with HMMs - EM for HMMs - Latent variable models: Factor Analysis - Introduction to Factor Analysis - Linear-Gaussian models - Probabilistic Principal Component Analysis - Probabilistic Linear Discriminant Analysis - Subspace models for GMMs
- Introduction to pattern classification - Decision theory - Classification model taxonomy - Generative probabilistic models - Discriminative probabilistic models - Decision functions - Model Evaluation - Binary classification - Accuracy measures - ROC / DET curves - Multiclass classification - Generative probabilistic models - Gaussian models - Gaussian mixture models - Expectation-Maximization for GMMs - Time-dependent models: Hidden Markov Models - Inference with HMMs - EM for HMMs - Latent variable models: Factor Analysis - Introduction to Factor Analysis - Linear-Gaussian models - Probabilistic Principal Component Analysis - Probabilistic Linear Discriminant Analysis - Subspace models for GMMs
Schedule: - Friday 08/03/2019 from 15:00 to 17:00 ROOM C - Monday 11/03/2019 from 15:00 to 18:00 ROOM C - Wednesday 13/03/2019 from 15:00 to 18:00 ROOM C - Friday 15/03/2019 from 15:00 to 18:00 ROOM C - Monday 18/03/2019 from 15:00 to 6:00 pm ROOM C - Wednesday 20/03/2019 from 15:00 to 18:00 ROOM C - Friday 22/03/2019 from 15:00 to 18:00 ROOM C
Schedule: - Friday 08/03/2019 from 15:00 to 17:00 ROOM C - Monday 11/03/2019 from 15:00 to 18:00 ROOM C - Wednesday 13/03/2019 from 15:00 to 18:00 ROOM C - Friday 15/03/2019 from 15:00 to 18:00 ROOM C - Monday 18/03/2019 from 15:00 to 6:00 pm ROOM C - Wednesday 20/03/2019 from 15:00 to 18:00 ROOM C - Friday 22/03/2019 from 15:00 to 18:00 ROOM C
ModalitÓ di esame:
Exam:
Gli studenti e le studentesse con disabilitÓ o con Disturbi Specifici di Apprendimento (DSA), oltre alla segnalazione tramite procedura informatizzata, sono invitati a comunicare anche direttamente al/la docente titolare dell'insegnamento, con un preavviso non inferiore ad una settimana dall'avvio della sessione d'esame, gli strumenti compensativi concordati con l'UnitÓ Special Needs, al fine di permettere al/la docente la declinazione pi¨ idonea in riferimento alla specifica tipologia di esame.
Exam:
In addition to the message sent by the online system, students with disabilities or Specific Learning Disorders (SLD) are invited to directly inform the professor in charge of the course about the special arrangements for the exam that have been agreed with the Special Needs Unit. The professor has to be informed at least one week before the beginning of the examination session in order to provide students with the most suitable arrangements for each specific type of exam.
Esporta Word


© Politecnico di Torino
Corso Duca degli Abruzzi, 24 - 10129 Torino, ITALY
Contatti