Boltzmann machines and energy-based models

Material for : Factored Conditional Restricted Boltzmann Machines for Modeling Motion Style ∗ Graham

In this document, we provide additional details for variants of Conditional Restricted Boltzmann Machines (CRBMs). Specifically we focus on each of the four models compared in the Quantitative Evaluation (Sec. 4.4). We collect the formulae required for contrastive divergence learning of parameters, synthesis from a trained model by alternating Gibbs samping, and forward prediction from a traine...

Actor-Critic Reinforcement Learning with Energy-Based Policies

We consider reinforcement learning in Markov decision processes with high dimensional state and action spaces. We parametrize policies using energy-based models (particularly restricted Boltzmann machines), and train them using policy gradient learning. Our approach builds upon Sallans and Hinton (2004), who parameterized value functions using energy-based models, trained using a non-linear var...

Training Restricted Boltzmann Machines with Overlapping Partitions

Restricted Boltzmann Machines (RBM) are energy-based models that are successfully used as generative learning models as well as crucial components of Deep Belief Networks (DBN). The most successful training method to date for RBMs is the Contrastive Divergence method. However, Contrastive Divergence is inefficient when the number of features is very high and the mixing rate of the Gibbs chain i...

Atomic Energy Models for Machine Learning: Atomic Restricted Boltzmann Machines

Continuous space language models using restricted Boltzmann machines

We present a novel approach for continuous space language models in statistical machine translation by using Restricted Boltzmann Machines (RBMs). The probability of an n-gram is calculated by the free energy of the RBM instead of a feedforward neural net. Therefore, the calculation is much faster and can be integrated into the translation process instead of using the language model only in a r...