Tanya L. Conroy

Learn More
N ONLINEAR signal processing systems are far more complex and have more interesting properties than their linear counterparts There are also less tools available for their analysis and any analysis tends to be less systematic than for linear processing There is therefore virtue in examining each nonlinear system on its merits In this thesis we proceed by(More)
Some signals, such as in radar systems, communication systems, and neural systems, are transmitted as periodic pulse trains. If more than one pulse train is transmitted over the same communication channel, a challenge is to separate them for source identification at the receiver. This is known as pulse train deinterleaving and is clearly a fundamental(More)
Many binary classi cation algorithms produce real-valued predictions which are then thresholded to produce a binary classi cation. These real-valued predictions can often be viewed as a measure of con dence in classi cation. Recent techniques for the theoretical analysis of such algorithms in terms of the classi cation con dence (or margin) have been(More)
  • 1