EBLearn: Open-Source Energy-Based Learning in C++

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 ef�...

• Type: Conference
• Year: 2009
• Where: ICTAI
• Authors: Pierre Sermanet, Koray Kavukcuoglu, Yann LeCun
• Keywords: Artificial Intelligence, Energy-based Learning, Energy-based Learning Models, ICTAI 2009, Latent Variables