Abstract. Segmentation of images is often posed as a variational problem. As such, it is solved by formulating an energy functional depending on a contour and other image derived t...
We present a novel semi-supervised training algorithm for learning dependency parsers. By combining a supervised large margin loss with an unsupervised least squares loss, a discr...
- In this paper, we show how a topographic mapping can be created from a product of experts. We learn the parameters of the mapping using gradient descent on the negative logarithm...
We present novel semi-supervised boosting algorithms that incrementally build linear combinations of weak classifiers through generic functional gradient descent using both labele...
In this paper, a recurrent neural network based fuzzy inference system (RNFIS) for prediction is proposed. A recurrent network is embedded in the RNFIS by adding feedback connecti...