177 search results - page 14 / 36 » Learning complex problem solving expertise from failures |
ICANN
2009
Springer
15 years 9 months ago
2009
Springer
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...
146
Voted
LAMAS
2005
Springer
15 years 8 months ago
2005
Springer
In this paper we report on using a relational state space in multi-agent reinforcement learning. There is growing evidence in the Reinforcement Learning research community that a r...
143
click to vote
TNN
2010
2010
Sensitivity versus accuracy in multiclass problems using memetic Pareto evolutionary neural networks
14 years 10 months ago
This paper proposes a multiclassification algorithm using multilayer perceptron neural network models. It tries to boost two conflicting main objectives of multiclassifiers: a high...
140
click to vote
ICML
1998
IEEE
16 years 4 months ago
1998
IEEE
This paper introduces the RL-TOPs architecture for robot learning, a hybrid system combining teleo-reactive planning and reinforcement learning techniques. The aim of this system ...
155
click to vote
SOCIALCOM
2010
14 years 10 months ago
2010
Weblogs (blogs) serve as a gateway to a large blog reader population, so blog authors can potentially influence a large reader population by expressing their thoughts and expertise...