We present a method based on statistical properties of local image pixels for focussing attention on regions of text in arbitrary scenes where the text plane is not necessarily fr...
This paper investigates a mechanism for reliable generation of sparse code in a sparsely connected, hierarchical, learning memory. Activity reduction is accomplished with local com...
Hierarchical clustering is used widely to organize data and search for patterns. Previous algorithms assume that the body of data being clustered is fixed while the algorithm runs...
H. Van Dyke Parunak, Richard Rohwer, Theodore C. B...
Learning data representations is a fundamental challenge in modeling neural processes and plays an important role in applications such as object recognition. In multi-stage Optima...
Recurrent neural networks are theoretically capable of learning complex temporal sequences, but training them through gradient-descent is too slow and unstable for practical use i...