This paper argues that multiagent learning is a potential “killer application” for generative and developmental systems (GDS) because key challenges in learning to coordinate ...
Evolution of neural networks, as implemented in NEAT, has proven itself successful on a variety of low-level control problems such as pole balancing and vehicle control. Nonethele...
The increased use of ubiquitous computing devices is resulting in networks that are highly mobile, well connected and growing in processing and storage capabilities. The nature of ...
Rudi Ball, James Grant, Jonathan So, Victoria Spur...
We investigate the problem of how to evaluate efficiently a collection of shortest path queries on massive graphs that are too big to fit in the main memory. To evaluate a shortes...
In this paper, we present techniques and algorithms to improve the performance of various communication patterns on message-passing platforms where, for reasons of safety, user-le...