Zobrazeno 1 - 5
of 5
pro vyhledávání: '"Zadrazil, Petr"'
Federated learning (FL) has shown promising results on training machine learning models with privacy preservation. However, for large models with over 100 million parameters, the training resource requirement becomes an obstacle for FL because common
Externí odkaz:
http://arxiv.org/abs/2408.10443
Autor:
Gooneratne, Mary, Sim, Khe Chai, Zadrazil, Petr, Kabel, Andreas, Beaufays, Françoise, Motta, Giovanni
Training machine learning models on mobile devices has the potential of improving both privacy and accuracy of the models. However, one of the major obstacles to achieving this goal is the memory limitation of mobile devices. Reducing training memory
Externí odkaz:
http://arxiv.org/abs/2001.08885
Autor:
Sim, Khe Chai, Beaufays, Françoise, Benard, Arnaud, Guliani, Dhruv, Kabel, Andreas, Khare, Nikhil, Lucassen, Tamar, Zadrazil, Petr, Zhang, Harry, Johnson, Leif, Motta, Giovanni, Zhou, Lillian
We study the effectiveness of several techniques to personalize end-to-end speech models and improve the recognition of proper names relevant to the user. These techniques differ in the amounts of user effort required to provide supervision, and are
Externí odkaz:
http://arxiv.org/abs/1912.09251
Speaker-independent speech recognition systems trained with data from many users are generally robust against speaker variability and work well for a large population of speakers. However, these systems do not always generalize well for users with ve
Externí odkaz:
http://arxiv.org/abs/1909.06678
Vývoj zemědělství na území obhospodařovaném bývalým státním statkem Chotěboř v rozmezí let 1945-2013
Autor:
Zadražil, Petr
Thesis analyzes development of agriculture between the years 1945-2013 in the concrete area which used to be covered by Chotěboř State Farm. For the whole time period, thesis analyzes general evolution of agriculture in Czechoslovakia (Czechia) as
Externí odkaz:
http://www.nusl.cz/ntk/nusl-312226