Analog VLSI and neural systems
Analog VLSI and neural systems
Neurocomputing
Learning internal representations by error propagation
Parallel distributed processing: explorations in the microstructure of cognition, vol. 1
A New Technique for Optimization Problems in Graph Theory
IEEE Transactions on Computers
A Neural Network Approach for Signal Detection in Digital Communications
Journal of VLSI Signal Processing Systems
Design rules for application specific dynamical systems
Computers and Operations Research
Combining competitive scheme with slack neurons to solve real-time job scheduling problem
Expert Systems with Applications: An International Journal
Solving inequality constraints job scheduling problem by slack competitive neural scheme
IEA/AIE'07 Proceedings of the 20th international conference on Industrial, engineering, and other applications of applied intelligent systems
A neural network string matcher
CAIP'07 Proceedings of the 12th international conference on Computer analysis of images and patterns
Journal of Systems Architecture: the EUROMICRO Journal
Solving multiprocessor real-time system scheduling with enhanced competitive scheme
ICONIP'06 Proceedings of the 13th international conference on Neural Information Processing - Volume Part II
Review: Artificial intelligence approaches to network management: recent advances and a survey
Computer Communications
Mathematical and Computer Modelling: An International Journal
Hi-index | 0.00 |
The design of feedback (or recurrent) neural networks to produce good solutions to complex optimization problems is discussed. The theoretical basis for applying neural networks to optimization problems is reviewed, and a design rule that serves as a primitive for constructing a wide class of constraints is introduced. The use of the design rule is illustrated by developing a neural network for producing high-quality solutions to a probabilistic resource allocation task. The resulting neural network has been simulated on a high-performance parallel processor that has been optimized for neural network simulation.