Sciweavers

4947 search results - page 406 / 990
» Learning Module Networks
Sort
View
ICANN
2009
Springer
16 years 1 months ago
Almost Random Projection Machine
Backpropagation of errors is not only hard to justify from biological perspective but also it fails to solve problems requiring complex logic. A simpler algorithm based on generati...
Wlodzislaw Duch, Tomasz Maszczyk
NIPS
1996
15 years 8 months ago
Monotonicity Hints
: Neural networks are competitive tools for classification problems. In this context, a hint is any piece of prior side information about the classification. Common examples are mo...
Joseph Sill, Yaser S. Abu-Mostafa
EWSN
2004
Springer
16 years 6 months ago
Context-Aware Sensors
Wireless sensor networks typically consist of a large number of sensor nodes embedded in a physical space. Such sensors are low-power devices that are primarily used for monitoring...
Eiman Elnahrawy, Badri Nath
ICRA
2009
IEEE
207views Robotics» more  ICRA 2009»
15 years 4 months ago
Bayesian network-based behavior control for skilligent robots
A Skilligent robot must be able to learn skills autonomously to accomplish a task. "Skilligence" is the capacity of the robot to control behaviors reasonably, based on th...
Sang Hyoung Lee, Il Hong Suh
ICARCV
2008
IEEE
200views Robotics» more  ICARCV 2008»
16 years 1 months ago
A robot behavior-learning experiment using Particle Swarm Optimization for training a neural-based animat
— We investigate the use of Particle Swarm Optimization (PSO), and compare with Genetic Algorithms (GA), for a particular robot behavior-learning task: the training of an animat ...
Fabien Moutarde