Sciweavers

1270 search results - page 242 / 254
» Dogged Learning for Robots
Sort
View
GECCO
2009
Springer
15 years 2 months ago
The sensitivity of HyperNEAT to different geometric representations of a problem
HyperNEAT, a generative encoding for evolving artificial neural networks (ANNs), has the unique and powerful ability to exploit the geometry of a problem (e.g., symmetries) by enc...
Jeff Clune, Charles Ofria, Robert T. Pennock
AIIDE
2006
14 years 11 months ago
The NERO Video Game
In most modern video games, character behavior is scripted; no matter how many times the player exploits a weakness, that weakness is never repaired. Yet if game characters could ...
Kenneth O. Stanley, Igor Karpov, Risto Miikkulaine...
IIE
2007
125views more  IIE 2007»
14 years 9 months ago
Should LOGO Keep Going FORWARD 1?
LOGO has been evolving in incremental steps for 40 years. This has resulted in steady progress but some regions of the space of all programming languages for children cannot be re...
Ken Kahn
IDA
2011
Springer
14 years 4 months ago
Ubiquitous Knowledge Discovery
Ubiquitous Knowledge Discovery is a new research area at the intersection of machine learning and data mining with mobile and distributed systems. In this paper the main character...
João Gama, Michael May
ICDM
2009
IEEE
112views Data Mining» more  ICDM 2009»
15 years 4 months ago
Spatio-temporal Multi-dimensional Relational Framework Trees
—The real world is composed of sets of objects that move and morph in both space and time. Useful concepts can be defined in terms of the complex interactions between the multi-...
Matthew Bodenhamer, Samuel Bleckley, Daniel Fennel...