National Repository of Grey Literature 1 records found  Search took 0.00 seconds. 
Optimalizační nástroj pro modely s hlubokým učením
FILIP, Václav
The goal of this thesis is to create a tool capable of optimizing parameters and structure of deep learning models. There are various ways to create a model like changing types and number of layers, various numerical parameters of the layers etc. These parameters greatly influence the quality of the model. Newly created tool is to offer functionalities not offered by any existing solution - these new functionalities are based on comparison of existing solutions. New solution is created in python.

Interested in being notified about new results for this query?
Subscribe to the RSS feed.