Title:  Classification and Recognition 

Code:  IKR 

Ac.Year:  2018/2019 

Sem:  Summer 

Curriculums:  

Language of Instruction:  Czech 

Public info:  http://www.fit.vutbr.cz/study/courses/IKR/public/ 

Credits:  5 

Completion:  examination (written&oral) 

Type of instruction:  Hour/sem  Lectures  Seminar Exercises  Laboratory Exercises  Computer Exercises  Other 

Hours:  26  13  0  0  13 

 Exams  Tests  Exercises  Laboratories  Other 

Points:  60  15  0  0  25 



Guarantor:  Burget Lukáš, doc. Ing., Ph.D. (DCGM) 

Deputy guarantor:  Černocký Jan, doc. Dr. Ing. (DCGM) 

Lecturer:  Burget Lukáš, doc. Ing., Ph.D. (DCGM) Černocký Jan, doc. Dr. Ing. (DCGM) Španěl Michal, Ing., Ph.D. (DCGM) 
Instructor:  Burget Lukáš, doc. Ing., Ph.D. (DCGM) 

Faculty:  Faculty of Information Technology BUT 

Department:  Department of Computer Graphics and Multimedia FIT BUT 

Prerequisites:  

Schedule: 

  Learning objectives: 

  To understand the foundations of machine learning with the focus on pattern classification and recognition. To learn how to apply basic algorithms and methods from this field to problems in speech and image recognition. To conceive basic principles of different generative an discriminative models for statistical pattern recognition. To get acquainted with the evaluation procedures.  Description: 

  The tasks of classification and pattern recognition, basic schema of a classifier, data and evaluation of individual methods, statistical pattern recognition, feature extraction, multivariate Gaussian distribution,, maximum likelihood estimation, Gaussian Mixture Model (GMM), Expectation Maximization (EM) algorithm, linear classifiers, perceptron, Gaussian Linear Classifier, logistic regression, support vector machines (SVM), feedforward neural networks, convolutional and recurrent neural networks, sequence classification, Hidden Markov Models (HMM). Applications of the methods to speech and image processing.
 Knowledge and skills required for the course: 

  Basic knowledge of the standard math notation.  Subject specific learning outcomes and competencies: 

  The students will get acquainted with the problem of machine learning applied to pattern classification and recognition. They will learn how to apply basic methods in the fields of speech processing and computer graphics. They will understand the common aspects and differences of the particular methods and will be able to take advantage of the existing classifiers in realsituations.  Generic learning outcomes and competencies: 

  The students will get acquainted with python libraries focused on math, linear algebra and machine learning. They will also improve their math skills (probability theory, statistics, linear algebra) a programming skills. The students will learn to work in a team.
 Why is the course taught: 

  Recent years witness a boom of machine learning or pattern recognition applications. More and more devices can be controlled using voice or gestures. Digital cameras automatically detect faces in the captured images in order to automatically focus or somehow react on it. Virtual agents in mobile devices can recognize speech and search for relevant answers to our queries. The quality of the current systems for automatic recognition of person's identity from voice recording or from face photo already significantly exceed the human abilities.
In this class, the students should learn how these technologies works. They will learn about the basic algorithms and models, which, using some training examples, automatically learn to recognize nontrivial patterns in audio recordings, images or other signals or input data.
 Syllabus of lectures: 


 The tasks of classification and pattern recognition, basic schema of a classifier, data sets and evaluation
 Probabilistic distributions, statistical pattern recognition
 Generative and discriminative models
 Multivariate Gaussian distribution, Maximum Likelihood estimation,
 Gaussian Mixture Model (GMM), Expectation
Maximization (EM)
 Feature extraction, Melfrequency cepstral coefficients.
 Application of the statistical models in speech and image processing.
 Linear classifiers, perceptron
 Gaussian
Linear Classifier, Logistic regression
 Support Vector Machines (SVM),
kernel functions
 Neural networks  feedforward, convolutional and recurrent
 Hidden Markov Models (HMM) and their application to speech recognition
 Project presentation
 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.
 Hart, P. E., Stork, D. G.:Pattern Classification (2nd ed), John Wiley &
Sons, 2000, ISBN: 9780471056690  Ian Goodfellow, Yoshua Bengio, and Aaron Courville. 2016. Deep Learning. The MIT Press.
 Study literature: 

  Bishop, C. M.: Pattern Recognition, Springer Science + Business Media, LLC, 2006, ISBN 0387310738.
 Hart, P. E., Stork, D. G.:Pattern Classification (2nd ed), John Wiley &Sons, 2000, ISBN: 9780471056690
 Controlled instruction: 

  The evaluation includes midterm test, individual project, and the final exam. The midterm test does not have a correction option, the final exam has two possible correction terms  Progress assessment: 

 
 Midterm test  up to 15 points
 Project  up to 25 points
 Written final exam  up to 60 points
 
