Many characteristics of functional synthetic siRNAs have been identified. Our three-phase algorithm was developed to design siRNA on a wholegenome scale based on these characteris...
We describe an approach to understanding evolved programs for a real world object detection problem, that of finding orthodontic landmarks in cranio-facial X-Rays. The approach in...
Victor Ciesielski, Andrew Innes, Sabu John, John M...
Policy gradient (PG) reinforcement learning algorithms have strong (local) convergence guarantees, but their learning performance is typically limited by a large variance in the e...
We propose a new method to control memory resources by static analysis. For this, we introduce the notion of sup-interpretation which bounds from above the size of function outputs...
Hidden Markov Models (HMMs) model sequential data in many fields such as text/speech processing and biosignal analysis. Active learning algorithms learn faster and/or better by cl...