Andrew Stout

Learn More
One of the primary challenges of developmental robotics is the question of how to learn and represent increasingly complex behavior in a self-motivated, open-ended way. 2004) have recently presented an algorithm for intrin-sically motivated reinforcement learning that strives to achieve broad competence in an environment in a task-nonspecific manner by(More)
Swarthmore's entries to this year's AAAI Mobile Robot competition won second place in the Urban Search and Rescue event and Third Place in the Robot Host competition. This article describes the features of Frodo and Rose, the two-robot team, and discusses their performance. The most important design feature that made the robots successful was a modular(More)
As artificial life systems grow in number and sophistication, it is becoming increasingly important that the field agree on principled metrics for evaluating them. This report describes a series of experiments validating the evolutionary activity statistics developed by Bedau and his colleagues [2, 3, 4]. The work described herein was motivated by a feeling(More)
ACKNOWLEDGMENTS Just before starting my PhD, I asked several acquaintances who had already been through the process for advice. I was given ominous warnings, told horror stories, and was generally advised to finish as quickly as possible and not look back. All these years later, I'm happy and grateful to be able to say that, quite contrary to their(More)
  • Binoy Appukuttan, Trevor J. McFarland, Andrew Stempel, Jean B. Kassem, Matthew Hartzell, Yi Zhang +11 others
  • 2012
Increased cellular production of vascular endothelial growth factor (VEGF) is responsible for the development and progression of multiple cancers and other neovascular conditions, and therapies targeting post-translational VEGF products are used in the treatment of these diseases. Development of methods to control and modify the transcription of the VEGF(More)
In the work described in this paper we undertook a fundamental, proof-of-concept exploration of an unsupervised technique for extracting and representing word meanings, called Latent Semantic Analysis. In this paper we detail an implementation of LSA for the purpose of vocabulary acquisition and report preliminary results from testing it on English(More)
  • 1