Course detail

Classification and recognition

FIT-KRDAcad. year: 2022/2023

Estimation of parameters Maximum Likelihood and Expectation-Maximization, formulation of the objective function of discriminative training, Maximum Mutual information (MMI) criterion, adaptation of GMM models, transforms of features for recognition, modelling of feature space using discriminative sub-spaces, factor analysis, kernel techniques, calibration and fusion of classifiers, applications in recognition of speech, video and text.

State doctoral exam - topics:

  1. Maximum Likelihood estimation of parameters of a model
  2. Probability distribution from the exponential family and sufficient statistics
  3. Linear regression model and its probabilistic interpretation
  4. Bayesian models considering the probability distribution (uncertainty) of model parameters
  5. Conjugate priors and their significance in Bayesian models
  6. Fishers linear discriminant analysis
  7. Difference between generative and discriminative classifiers; their pros and cons
  8. Perceptron and its learning algorithm as an example of linear classifiers
  9. Generative linear classifier - Gaussian classifier with shared covariance matrix
  10. Discriminative classifier based on linear logistic regression

Language of instruction

Czech

Number of ECTS credits

0

Mode of study

Not applicable.

Learning outcomes of the course unit

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.

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

Prerequisites

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

Co-requisites

Not applicable.

Planned learning activities and teaching methods

Not applicable.

Assesment methods and criteria linked to learning outcomes

Not applicable.

Course curriculum

Not applicable.

Work placements

Not applicable.

Aims

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.

Specification of controlled education, way of implementation and compensation for absences

Oral exam.

Recommended optional programme components

Not applicable.

Prerequisites and corequisites

Not applicable.

Basic literature

Not applicable.

Recommended reading

Ian Goodfellow, Yoshua Bengio, Aaron Courville: Deep Learning, MIT Press, 2016.
Simon Haykin: Neural Networks And Learning Machines, Pearson Education; Third edition, 2016.

Classification of course in study plans

  • Programme VTI-DR-4 Doctoral

    branch DVI4 , any year of study, summer semester, elective

  • Programme VTI-DR-4 Doctoral

    branch DVI4 , any year of study, summer semester, elective

  • Programme VTI-DR-4 Doctoral

    branch DVI4 , any year of study, summer semester, elective

  • Programme VTI-DR-4 Doctoral

    branch DVI4 , any year of study, summer semester, elective

  • Programme DIT-EN Doctoral, any year of study, summer semester, compulsory-optional
  • Programme DIT Doctoral, any year of study, summer semester, compulsory-optional
  • Programme DIT Doctoral, any year of study, summer semester, compulsory-optional
  • Programme DIT-EN Doctoral, any year of study, summer semester, compulsory-optional

Type of course unit

 

Lecture

39 hours, optionally

Teacher / Lecturer

Syllabus

  1. Estimation of parameters of Gaussian probability distribution by Maximum Likelihood (ML)
  2. Estimation of parameters of Gaussian Gaussian Mixture Model (GMM) by Expectation-Maximization (EM)
  3. Discriminative training, introduction, formulation of the objective function
  4. Discriminative training with the Maximum Mutual information (MMI) criterion
  5. Adaptation of GMM models- Maximum A-Posteriori (MAP), Maximum Likelihood Linear Regression (MLLR)
  6. Transforms of features for recognition - basis, Principal component analysis (PCA)
  7. Discriminative transforms of features - Linear Discriminant Analysis (LDA) and Heteroscedastic Linear Discriminant Analysis  (HLDA)
  8. Modeling of feature space using discriminative sub-spaces - factor analysis
  9. Kernel techniques, SVM
  10. Calibration and fusion of classifiers
  11. Applications in recognition of speech, video and text
  12. Student presentations I
  13. Student presentations II

Guided consultation in combined form of studies

26 hours, optionally

Teacher / Lecturer