Eine Plattform für die Wissenschaft: Bauingenieurwesen, Architektur und Urbanistik
Eine Plattform für die Wissenschaft: Bauingenieurwesen, Architektur und Urbanistik
Lie group impression for deep learning
In this work, we exploit a novel algorithm for capturing the Lie group manifold structure of the visual impression. By developing the single-layer Lie group model, we show how the representation learning algorithm can be stacked to yield a deep architecture. In addition, we design a Lie group based gradient descent algorithm to solve the learning problem of network weights. We show that our proposed technique yields representations that significantly better suited for training deep network and is also computationally efficient.
Lie group impression for deep learning
In this work, we exploit a novel algorithm for capturing the Lie group manifold structure of the visual impression. By developing the single-layer Lie group model, we show how the representation learning algorithm can be stacked to yield a deep architecture. In addition, we design a Lie group based gradient descent algorithm to solve the learning problem of network weights. We show that our proposed technique yields representations that significantly better suited for training deep network and is also computationally efficient.
Lie group impression for deep learning
Yang, Mengduo (Autor:in) / Li, Fanzhang (Autor:in)
01.09.2017
220507 byte
Aufsatz (Konferenz)
Elektronische Ressource
Englisch
Deep learning algorithm with visual impression
| IEEE | 2017
| Online Contents | 2000
| DataCite | 1917
| British Library Online Contents | 1997