Abstract. Recently, the authors described a training method for a convolutional neural network of threshold neurons. Hidden layers are trained by by clustering, in a feed-forward m...
Johannes Fieres, Karlheinz Meier, Johannes Schemme...
In statistical pattern recognition, parameters of distributions are usually estimated from training samples. It is well known that shortage of training samples causes estimation e...
We study the low-level problem of predicting pixel intensities after subpixel image translations. This is a basic subroutine for image warping and super-resolution, and it has a c...
Abstract. The ability to generate narrative is of importance to computer systems that wish to use story effectively for entertainment, training, or education. One of the focuses of...
The ability to generate narrative is of importance to computer systems that wish to use story effectively for entertainment, training, or education. We identify two properties of ...