Crinohttp://mloss.orgUpdates and additions to CrinoenWed, 16 Jul 2014 17:54:55 -0000Crino 1.0.0<html><p>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. </p> <p>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 : </p> <ul> <li> auto-encoders (AE) </li> <li> multi-layer perceptrons (MLP) </li> <li> deep neural networks (DNN) </li> <li> input-output deep architectures (IODA) </li> </ul> <p>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. </p> <p>If you use Crino and/or our IODA framework for academic research, you are highly encouraged (though not required) to cite the following paper: </p> <ul> <li> 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] </li> </ul></html>clement chatelain, romain herault, julien lerouge, romain modzelewskiWed, 16 Jul 2014 17:54:55 -0000 learningneural networksgpu