The Community for Technology Leaders
2009 21st IEEE International Conference on Tools with Artificial Intelligence (2009)
Newark, New Jersey
Nov. 2, 2009 to Nov. 4, 2009
ISSN: 1082-3409
ISBN: 978-0-7695-3920-1
pp: 693-697
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. 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 EBLearn to enable the construction of energy-based learning models. EBLearn is composed of two major components, libidx: an efficient and 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.
energy-based learning, convolutional neural netwoks, open-source

K. Kavukcuoglu, P. Sermanet and Y. LeCun, "EBLearn: Open-Source Energy-Based Learning in C++," 2009 21st IEEE International Conference on Tools with Artificial Intelligence(ICTAI), Newark, New Jersey, 2009, pp. 693-697.
97 ms
(Ver 3.3 (11022016))