ATIAM Machine Learning & Music Course

logo_atiam3.jpg Instructors: Arshia Cont and Mathieu Lagrange

This course provides an introduction to pattern recognition and statistical learning for the ATIAM Masters at Ircam during the school year 2012-2013. The goal of the course series is to expose students to problem solving tools using machine learning techniques and intuitions behind each approach.

Topics covered include: Bayesian decision theory; parameter estimation; maximum likelihood; Bayesian parameter estimation; conjugate and non-informative priors; dimensionality and dimensionality reduction; principal component analysis; linear discriminant analysis; density estimation: parametric vs. kernel-based methods; Nearest Neighbor methods; mixture models; expectation-maximization; Sequential Learning; HMMs; Computational Auditory Analysis; Source Separation; and musical applications.

Lectures

Topics Material
12/11/2012, 10H
Arshia Cont
Basics, Bayesian Learning and Parameter Estimation Slides
5/12/2012, 14H30
Arshia Cont
Non-parametric Learning, Clustering, Sequential Learning Slides
11/12/2012, 10H
Mathieu Lagrange
Intro to machine learning in music Slides
11/12/2012, 14h30
Mathieu Lagrange
Sound source segregation: from the brain to the machine Slides ASA
Slides BSS
12/12/2012, 9h30 (ENST)
Mathieu Lagrange
TD

Group Homeworks

# Topics Material
0 Gaussian Linear Discriminant Formulation pdf
1 Maximum Likelihood on Polynomial Refression pdf
2 Bayesian Parameter Estimation on Multinomial/histogram problems pdf
3 EM for exponential families pdf

Resources

Grading

The final exam and TD notes contribute to 50% of the STIM grading.

 


atiam_ml_2012.txt · Dernière modification: 2012/12/15 16:35 par Arshia Cont