Sciweavers

527 search results - page 99 / 106
» Design beyond human abilities
Sort
View
ATAL
2005
Springer
14 years 1 months ago
Improving reinforcement learning function approximators via neuroevolution
Reinforcement learning problems are commonly tackled with temporal difference methods, which use dynamic programming and statistical sampling to estimate the long-term value of ta...
Shimon Whiteson
KDD
2009
ACM
167views Data Mining» more  KDD 2009»
14 years 8 months ago
Seven pitfalls to avoid when running controlled experiments on the web
Controlled experiments, also called randomized experiments and A/B tests, have had a profound influence on multiple fields, including medicine, agriculture, manufacturing, and adv...
Thomas Crook, Brian Frasca, Ron Kohavi, Roger Long...
MOBISYS
2004
ACM
14 years 7 months ago
Energy-Efficient Surveillance System Using Wireless Sensor Networks
The focus of surveillance missions is to acquire and verify information about enemy capabilities and positions of hostile targets. Such missions often involve a high element of ri...
Tian He, Sudha Krishnamurthy, John A. Stankovic, T...
ACSAC
2005
IEEE
14 years 1 months ago
PorKI: Making User PKI Safe on Machines of Heterogeneous Trustworthiness
As evidenced by the proliferation of phishing attacks and keystroke loggers, we know that human beings are not wellequipped to make trust decisions about when to use their passwor...
Sara Sinclair, Sean W. Smith
GECCO
2009
Springer
14 years 3 days 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