Energy-based learning (EBL) is a general framework to describe supervised and unsupervised training methods for probabilistic and non-probabilistic factor graphs. An energy-based model associates a scalar energy to configurations of inputs, outputs, and latent variables. Inference consists in finding configurations of output and latent variables that minimize the energy. Learning consists in finding parameters that minimize a suitable loss function so that the module produces lower energies for “correct” outputs than for all “incorrect ” outputs. Learning machines can be constructed by assembling modules and loss functions. Gradient-based learning procedures are easily implemented through semi-automatic differentiation of complex models constructed by assembling predefined modules. We introduce an open-source and cross-platform C++ library called EBLearn1 to enable the construction of energy-based learning models. EBLearn is composed of two major components, libidx: an efficient and very flexible multi-dimensional tensor library, and libeblearn: an object-oriented library of trainable modules and learning algorithms. The latter has facilities for such models as convolutional networks, as well as for image processing. It also provides graphical display functions. 1.
Description
CiteSeerX — EBLearn: Open-Source Energy-Based Learning in C++
%0 Generic
%1 Sermanet_eblearn:open-source
%A Sermanet, Pierre
%A Kavukcuoglu, Koray
%A Lecun, Yann
%D 2009
%K C++ CNN EBLearn Implementation
%T EBLearn: Open-Source Energy-Based Learning in C++
%U http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.158.9936
%X Energy-based learning (EBL) is a general framework to describe supervised and unsupervised training methods for probabilistic and non-probabilistic factor graphs. An energy-based model associates a scalar energy to configurations of inputs, outputs, and latent variables. Inference consists in finding configurations of output and latent variables that minimize the energy. Learning consists in finding parameters that minimize a suitable loss function so that the module produces lower energies for “correct” outputs than for all “incorrect ” outputs. Learning machines can be constructed by assembling modules and loss functions. Gradient-based learning procedures are easily implemented through semi-automatic differentiation of complex models constructed by assembling predefined modules. We introduce an open-source and cross-platform C++ library called EBLearn1 to enable the construction of energy-based learning models. EBLearn is composed of two major components, libidx: an efficient and very flexible multi-dimensional tensor library, and libeblearn: an object-oriented library of trainable modules and learning algorithms. The latter has facilities for such models as convolutional networks, as well as for image processing. It also provides graphical display functions. 1.
@misc{Sermanet_eblearn:open-source,
abstract = {Energy-based learning (EBL) is a general framework to describe supervised and unsupervised training methods for probabilistic and non-probabilistic factor graphs. An energy-based model associates a scalar energy to configurations of inputs, outputs, and latent variables. Inference consists in finding configurations of output and latent variables that minimize the energy. Learning consists in finding parameters that minimize a suitable loss function so that the module produces lower energies for “correct” outputs than for all “incorrect ” outputs. Learning machines can be constructed by assembling modules and loss functions. Gradient-based learning procedures are easily implemented through semi-automatic differentiation of complex models constructed by assembling predefined modules. We introduce an open-source and cross-platform C++ library called EBLearn1 to enable the construction of energy-based learning models. EBLearn is composed of two major components, libidx: an efficient and very flexible multi-dimensional tensor library, and libeblearn: an object-oriented library of trainable modules and learning algorithms. The latter has facilities for such models as convolutional networks, as well as for image processing. It also provides graphical display functions. 1.},
added-at = {2013-03-21T11:34:18.000+0100},
author = {Sermanet, Pierre and Kavukcuoglu, Koray and Lecun, Yann},
biburl = {https://www.bibsonomy.org/bibtex/213e8e0ab3b994f15d95a77c890d4be23/andre@ismll},
description = {CiteSeerX — EBLearn: Open-Source Energy-Based Learning in C++},
interhash = {a37c215bd8d3344d996c76c547eb7b50},
intrahash = {13e8e0ab3b994f15d95a77c890d4be23},
keywords = {C++ CNN EBLearn Implementation},
timestamp = {2013-03-21T11:34:18.000+0100},
title = {EBLearn: Open-Source Energy-Based Learning in C++},
url = {http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.158.9936},
year = 2009
}