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.
Crino lets you "hand-craft" neural-network architectures, using a modular framework inspired by Torch. Our library also provides standard implementations as long as learning algorithms for :
- auto-encoders (AE)
- multi-layer perceptrons (MLP)
- deep neural networks (DNN)
- input-output deep architectures (IODA)
IODA is a novel DNN architecture, 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.
If you use Crino and/or our IODA framework for academic research, you are highly encouraged (though not required) to cite the following paper:
- J. Lerouge, R. Herault, C. Chatelain, F. Jardin and R. Modzelewski, "IODA: an Input/Output Deep Architecture for image labeling", Pattern Recognition (2015), DOI: 10.1016/j.patcog.2015.03.017 [Epub ahead of print]
- Changes to previous version:
1.0.0 (7 july 2014) : - Initial release of crino - Implements a torch-like library to build artificial neural networks (ANN) - Provides standard implementations for : * auto-encoders * multi-layer perceptrons (MLP) * deep neural networks (DNN) * input output deep architecture (IODA) - Provides a batch-gradient backpropagation algorithm, with adaptative learning rate
No one has posted any comments yet. Perhaps you'd like to be the first?
Leave a comment
You must be logged in to post comments.