Gabrielle Horne

Learn More
We present two approaches to the analysis of the relationship between a recurrent neural network (RNN) and the nite state machine M the network is able to exactly mimic. First, the network is treated as a state machine and the relationship between the RNN and M is established in the context of algebraic theory of automata. In the second approach, the RNN is(More)
BACKGROUND Women with connective tissue disorders are at risk for cardiovascular complications during pregnancy, but there are no guidelines for pregnant women with aortic root diameter>45 mm or with rapid aortic widening. We describe the issues of practical significance in the management of pregnancy and delivery in a woman with Marfan syndrome (MFS). (More)
In this paper, the detection of the boundaries and extraction of the area of left ventricular are proposed. The echocardiographic image is preprocessed to enhance the contrast and smoothness by utilizing Multi Valued Neural Cellular Neural Networks (MVN_CNN) non linear filter. UBN_CNN is applied to the smoothed image to detect the heart boundaries. A non(More)
Data fusion is an important tool for improving the performance of a detection system when more than one classifier is available. The reasoning logic of Dempster-Shafer evidence theory for fusion is similar to that of humans. This paper discusses application of a data fusion method which is based on improvements to the Dempster-Shafer theory, to(More)
  • 1