Title:  Classification and recognition 

Code:  KRD 

Ac.Year:  2017/2018 

Term:  Summer 

Curriculums:  

Language:  Czech 

Completion:  examination 

Type of instruction:  Hour/sem  Lectures  Sem. Exercises  Lab. exercises  Comp. exercises  Other 

Hours:  39  0  0  0  0 

 Examination  Tests  Exercises  Laboratories  Other 

Points:  60  0  0  0  40 



Guarantee:  Smrž Pavel, doc. RNDr., Ph.D., DCGM 

Lecturer:  Burget Lukáš, doc. Ing., Ph.D., DCGM 
Faculty:  Faculty of Information Technology BUT 

Department:  Department of Computer Graphics and Multimedia FIT BUT 


Learning objectives: 

  To
understand advanced classification and recognition techniques and to
learn how to apply the
algorithms and methods to problems in speech recognition,
computer graphics and natural language processing. To get acquainted with discriminative training and building hybrid
systems. 
Description: 

  Estimation of parameters Maximum Likelihood and ExpectationMaximization, formulation of the objective function of discriminative training, Maximum Mutual information (MMI) criterion, adaptation of GMM models, transforms of features for recognition, modeling of feature space using discriminative subspaces, factor analysis, kernel techniques, calibration and fusion of classifiers, applications in recognition of speech, video and text. 
Knowledge and skills required for the course: 

  Basic knowledge of statistics, probability theory, mathematical analysis and algebra.

Subject specific learning outcomes and competences: 

  The students will get acquainted with advanced classification and recognition
techniques and learn how to apply basic methods in the fields of speech
recognition, computer graphics and natural language processing.

Generic learning outcomes and competences: 

  The students will learn to solve general problems of classification and recognition.

Syllabus of lectures: 

  Estimation of parameters of Gaussian probability distribution by Maximum Likelihood (ML)
 Estimation of parameters of Gaussian Gaussian Mixture Model (GMM) by ExpectationMaximization (EM)
 Discriminative training, introduction, formulation of the objective function
 Discriminative training with the Maximum Mutual information (MMI) criterion
 Adaptation of GMM models Maximum APosteriori (MAP), Maximum Likelihood Linear Regression (MLLR)
 Transforms of features for recognition  basis, Principal component analysis (PCA)
 Discriminative transforms of features  Linear Discriminant Analysis (LDA) and Heteroscedastic Linear Discriminant Analysis (HLDA)
 Modeling of feature space using discriminative subspaces  factor analysis
 Kernel techniques, SVM
 Calibration and fusion of classifiers
 Applications in recognition of speech, video and text
 Student presentations I
 Student presentations II

Syllabus  others, projects and individual work of students: 

  Individually assigned projects

Fundamental literature: 

  Bishop, C. M.: Pattern Recognition, Springer Science + Business Media, LLC, 2006, ISBN 0387310738.
 Fukunaga, K.
Statistical pattern recognition, Morgan Kaufmann, 1990, ISBN 0122698517.

Study literature: 

  Bishop, C. M.: Pattern Recognition, Springer Science + Business Media, LLC, 2006, ISBN 0387310738.

Controlled instruction: 

  The evaluation includes the individual project 
