Servizi per la didattica
PORTALE DELLA DIDATTICA

Mimetic learning

03QTIIU

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
Squillero Giovanni   Professore Associato ING-INF/05 20 0 0 0 8
Teaching assistant
Espandi

Context
SSD CFU Activities Area context
*** N/A ***    
2018/19
Period: JULY The course illustrates several heuristic methodologies able to tackle complex problems. While the techniques differ in many respects, they all share an attempt to learn the optimal strategy by mimicking natural processes.
Period: JULY The course illustrates several heuristic methodologies able to tackle complex problems. While the techniques differ in many respects, they all share an attempt to learn the optimal strategy by mimicking natural processes.
The course introduces the vast family of algorithms that have been labeled either “machine learning” or “evolutionary algorithms”, and puts them into an historical perspective. Differences and correlations among the different approaches are shown, together with the backgrounds and the breakthroughs that led to the current “Deep learning” hype. In more details: • Introduction to (Evolutionary) Machine Learning and Computational Intelligence o Taxonomy: Classification, regression, clustering o Representation Learning o Deep learning o Included a crash course on Python/Jupyter and other tools used in data science • Evolutionary algorithms and Evolutionary Machine Learning o Classic paradigms (Genetic Algorithm, Genetic Programming, Evolution Strategies, and Evolutionary Programming) o Particle-Swarm Optimization and Ant-Colony Optimization o Differential Evolution o Estimation of Distribution Algorithm o Artificial Immune Systems • Rule-Based Systems o Learning Classifier Systems Mimetic Learning belongs to an educational path on Data Science. The path is composed by an introductory course covering data analytics fundamentals, which is a cultural prerequisite for the other courses (Data Mining: Concepts and Algorithms), and other four thematic courses dealing in depth with specific topics, algorithm types and application domains: Data Analytics for Science and Society; Machine Learning for Pattern Recognition; Text Mining and Analytics; Visualization and Visual Analytics.
The course introduces the vast family of algorithms that have been labeled either “machine learning” or “evolutionary algorithms”, and puts them into an historical perspective. Differences and correlations among the different approaches are shown, together with the backgrounds and the breakthroughs that led to the current “Deep learning” hype. In more details: • Introduction to (Evolutionary) Machine Learning and Computational Intelligence o Taxonomy: Classification, regression, clustering o Representation Learning o Deep learning o Included a crash course on Python/Jupyter and other tools used in data science • Evolutionary algorithms and Evolutionary Machine Learning o Classic paradigms (Genetic Algorithm, Genetic Programming, Evolution Strategies, and Evolutionary Programming) o Particle-Swarm Optimization and Ant-Colony Optimization o Differential Evolution o Estimation of Distribution Algorithm o Artificial Immune Systems • Rule-Based Systems o Learning Classifier Systems Mimetic Learning belongs to an educational path on Data Science. The path is composed by an introductory course covering data analytics fundamentals, which is a cultural prerequisite for the other courses (Data Mining: Concepts and Algorithms), and other four thematic courses dealing in depth with specific topics, algorithm types and application domains: Data Analytics for Science and Society; Machine Learning for Pattern Recognition; Text Mining and Analytics; Visualization and Visual Analytics.
Le lezioni si terranno nella prima settimana di luglio presso l'ACSLAB dal 01/07 al 05/07 nell'orario 09:00-13:00.
Le lezioni si terranno nella prima settimana di luglio presso l'ACSLAB dal 01/07 al 05/07 nell'orario 09:00-13:00.
Modalità di esame:
Exam:
Esporta Word


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