Zobrazeno 1 - 10
of 545
pro vyhledávání: '"Ritchie, J. M."'
Designing architectures for deep neural networks requires expert knowledge and substantial computation time. We propose a technique to accelerate architecture selection by learning an auxiliary HyperNet that generates the weights of a main model cond
Externí odkaz:
http://arxiv.org/abs/1708.05344
The early layers of a deep neural net have the fewest parameters, but take up the most computation. In this extended abstract, we propose to only train the hidden layers for a set portion of the training run, freezing them out one-by-one and excludin
Externí odkaz:
http://arxiv.org/abs/1706.04983
The increasingly photorealistic sample quality of generative image models suggests their feasibility in applications beyond image generation. We present the Neural Photo Editor, an interface that leverages the power of generative neural networks to m
Externí odkaz:
http://arxiv.org/abs/1609.07093
When working with three-dimensional data, choice of representation is key. We explore voxel-based models, and present evidence for the viability of voxellated representations in applications including shape modeling and object classification. Our key
Externí odkaz:
http://arxiv.org/abs/1608.04236
Autor:
Ritchie, J. M., author
Publikováno v:
‘Totally un-English’?: Britain’s Internment of ‘Enemy Aliens’ in Two World Wars. :193-203
Autor:
Thunecke, Jörg, author, Ritchie, J. M., author
Publikováno v:
Deutschsprachige Exillyrik von 1933 bis zur Nachkriegszeit. :217-234