Zobrazeno 1 - 2
of 2
pro vyhledávání: '"Olivier Breuleux"'
Publikováno v:
Neural Computation. 23:2058-2073
Two recently proposed learning algorithms, herding and fast persistent contrastive divergence (FPCD), share the following interesting characteristic: they exploit changes in the model parameters while sampling in order to escape modes and mix better
Autor:
Joseph Turian, Yoshua Bengio, Frédéric Bastien, Razvan Pascanu, David Warde-Farley, Guillaume Desjardins, James Bergstra, Olivier Breuleux, Pascal Lamblin
Publikováno v:
Proceedings of the Python in Science Conference.
Theano is a compiler for mathematical expressions in Python that combines the convenience of NumPy's syntax with the speed of optimized native machine language. The user composes mathematical expressions in a high-level description that mimics NumPy'