— A learning machine is called singular if its Fisher information matrix is singular. Almost all learning machines used in information processing are singular, for example, layer...
The problem of learning metrics between structured data (strings, trees or graphs) has been the subject of various recent papers. With regard to the specific case of trees, some a...
Factored representations, model-based learning, and hierarchies are well-studied techniques for improving the learning efficiency of reinforcement-learning algorithms in large-sca...
Carlos Diuk, Alexander L. Strehl, Michael L. Littm...
Recent work on unsupervised feature learning has shown that learning on polynomial expansions of input patches, such as on pair-wise products of pixel intensities, can improve the...
Inhomogeneous Gibbs model (IGM) [4] is an effective maximum entropy model in characterizing complex highdimensional distributions. However, its training process is so slow that th...