In this paper, an optimized approximation algorithm (OAA) is proposed to address the overfitting problem in function approximation using neural networks (NNs). The optimized approx...
In order to effectively use machine learning algorithms, e.g., neural networks, for the analysis of survival data, the correct treatment of censored data is crucial. The concordan...
If a moving image is more expressive than words or than a still image, then an animated facial expression can explain more in depth the feelings of a virtual character. Facial ani...
We present Galileo, an innovative engineering modeling and analysis tool built using an approach we call packageoriented programming (POP). Galileo represents an ongoing evaluatio...
Correspondence algorithms typically struggle with shapes that display part-based variation. We present a probabilistic approach that matches shapes using independent part transfor...