Package crino
[hide private]
[frames] | no frames]

Package crino

source code

Crino: a neural-network library based on Theano

Crino is an open-source Python library aimed at building and training artificial neural-networks. It has been developed on top of Theano, by researchers from the LITIS laboratory. It helps scientists and/or programmers to design neural-network architectures adapted to their needs, using a modular framework inspired by Torch. Our library also provides vanilla implementations, and learning algorithms, for these architectures :

IODA is an extension of DNN architectures, which is useful in cases where both input and output spaces are high-dimensional, and where there are strong interdependences between output labels. The input and output layers of a IODA are initialized with an unsupervised pre-training step, based on the stacked auto-encoder strategy, commonly used in DNN training algorithms. Then, the backpropagation algorithm performs the final supervised learning step.

Crino and IODA are research topics of the Deep in Normandy research program, which is a NVIDIA GPU Research Center.

See Also: GitHub repository, Project homepage

Version: 0.2.0

Submodules [hide private]
  • crino.criterion: The criterion module provides some differentiable loss functions in order to perform a gradient descent on a hand-crafted neural network.
  • crino.module: The module module provides a modular architecture to build a neural network.
  • The network module provides some ready-to-use neural network architectures, along with pretraining and supervised learning methods.