Sciweavers

626 search results - page 36 / 126
» Evolving Artificial Neural Networks that Develop in Time
Sort
View
103
Voted
CEC
2008
IEEE
15 years 7 months ago
Learning what to ignore: Memetic climbing in topology and weight space
— We present the memetic climber, a simple search algorithm that learns topology and weights of neural networks on different time scales. When applied to the problem of learning ...
Julian Togelius, Faustino J. Gomez, Jürgen Sc...
127
Voted
CISIM
2008
IEEE
15 years 7 months ago
Evolution Induced Secondary Immunity: An Artificial Immune System Based Intrusion Detection System
The analogy between Immune Systems and Intrusion Detection Systems encourage the use of Artificial Immune Systems for anomaly detection in computer networks. This paper describes ...
Divyata Dal, Siby Abraham, Ajith Abraham, Sugata S...
EAAI
2006
123views more  EAAI 2006»
15 years 18 days ago
Applications of artificial intelligence for optimization of compressor scheduling
This paper presents a feasibility study of evolutionary scheduling for gas pipeline operations. The problem is complex because of several constraints that must be taken into consi...
Hanh H. Nguyen, Christine W. Chan
FPL
2003
Springer
144views Hardware» more  FPL 2003»
15 years 5 months ago
FPGA Implementations of Neural Networks - A Survey of a Decade of Progress
The first successful FPGA implementation [1] of artificial neural networks (ANNs) was published a little over a decade ago. It is timely to review the progress that has been made i...
Jihan Zhu, Peter Sutton
94
Voted
AI
2002
Springer
15 years 13 days ago
Programming backgammon using self-teaching neural nets
TD-Gammon is a neural network that is able to teach itself to play backgammon solely by playing against itself and learning from the results. Starting from random initial play, TD...
Gerald Tesauro