National Repository of Grey Literature 6 records found  Search took 0.00 seconds. 
Handwritten Digit Recognition Using K-nearest Neighbor
Horký, Vladimír ; Mikolov, Tomáš (referee) ; Plchot, Oldřich (advisor)
This paper describes problems of handwritten digit recognition. Discuss about problems with solution of recognition by algorithm K-nearests neighbor. In second part there is described design and implementation of this method.
Handwritten Character Recognition Using Artificial Neural Networks
Horký, Vladimír ; Janda, Miloš (referee) ; Plchot, Oldřich (advisor)
Neural networks with algorithm back-propagation will be presented in this work. Theoretical background of the algorithm will be explained. The problems with training neural nets will be solving there. The work discuss some techniques of image preprocessing and image extraction features, which is one of main part in classification. Some part of work discuss few experiments with neural nets with chosen image features.
An Interactive Game for Child Psychotherapy
Hořký, Vladimír ; Pešková, Klára (advisor) ; Holan, Tomáš (referee)
Play is a natural way for children to communicate, and traditional games and toys are commonly used in child psychotherapy. Despite the increasing popularity of computer games among children, their use in child psychotherapy is not yet widespread. This thesis focuses on the development of a computer game to aid psychotherapists working with children aged approximately five to ten years. The game features Octopus as the main character, and children under the supervision of their therapist can experience four different adventures, including avoiding obstacles in the sea, balancing on seaweed, dressing up, and riding out a storm. The game is designed to prompt discussions with the therapist. The development of the game was iterative, with collaboration from a child psychologist and a graphic artist. Three child psychologists tested the game in practice with approximately twenty children and found it to be a useful therapeutic tool. 1
Handwritten Digit Recognition Using K-nearest Neighbor
Horký, Vladimír ; Mikolov, Tomáš (referee) ; Plchot, Oldřich (advisor)
This paper describes problems of handwritten digit recognition. Discuss about problems with solution of recognition by algorithm K-nearests neighbor. In second part there is described design and implementation of this method.
Handwritten Character Recognition Using Artificial Neural Networks
Horký, Vladimír ; Janda, Miloš (referee) ; Plchot, Oldřich (advisor)
Neural networks with algorithm back-propagation will be presented in this work. Theoretical background of the algorithm will be explained. The problems with training neural nets will be solving there. The work discuss some techniques of image preprocessing and image extraction features, which is one of main part in classification. Some part of work discuss few experiments with neural nets with chosen image features.

See also: similar author names
6 Horký, Vladimír
5 Horký, Vojtěch
3 Horký, Václav
2 Horký, Vít
Interested in being notified about new results for this query?
Subscribe to the RSS feed.