Combining machine learning models is a means of improving overall accuracy.Various algorithms have been proposed to create aggregate models from other models, and two popular examp...
Continuous Time Recurrent Neural Networks (CTRNNs) have previously been proposed as an enabling paradigm for evolving analog electrical circuits to serve as controllers for physica...
In this paper, we propose a learning-based image restoration algorithm for restoring images degraded by uniform motion blurs. The motion blur parameters are first approximately es...
We introduce an algorithm for learning a local metric to a continuous input space that measures distances in terms of relevance to the processing task. The relevance is defined a...
Cheap and versatile cameras make it possible to easily and quickly capture a wide variety of documents. However, low resolution cameras present a challenge to OCR because it is vi...
Charles E. Jacobs, Patrice Y. Simard, Paul A. Viol...