Restricted Boltzmann machines were developed using binary stochastic hidden units. These can be generalized by replacing each binary unit by an infinite number of copies that all ...
This paper summarizes two studies and the contemporary literature on the design and construction of effective and efficient Computer Based Learning (CBL) environments. There is ade...
We propose a simple approach to combining first-order logic and probabilistic graphical models in a single representation. A Markov logic network (MLN) is a first-order knowledge b...
This paper describes an integrated model for the realization of an Open and Distance Learning (ODL) environment supporting traditional learning procedures, through collaborative le...
Abstract-- Policy Gradients with Parameter-based Exploration (PGPE) is a novel model-free reinforcement learning method that alleviates the problem of high-variance gradient estima...
Frank Sehnke, Alex Graves, Christian Osendorfer, J...