Neural networks and fuzzy systems: a dynamical systems approach to machine intelligence
Neural networks and fuzzy systems: a dynamical systems approach to machine intelligence
Analog Integrated Circuits and Signal Processing - Special issue on Learning on Silicon
Frequency-based multilayer neural network with on-chip learning and enhanced neuron characteristics
IEEE Transactions on Neural Networks
Deterministic bit-stream digital neurons
IEEE Transactions on Neural Networks
A new digital pulse-mode neuron with adjustable activation function
IEEE Transactions on Neural Networks
IEEE Transactions on Neural Networks
Implementation of a new neurochip using stochastic logic
IEEE Transactions on Neural Networks
Analog and digital FPGA implementation of BRIN for optimization problems
IEEE Transactions on Neural Networks
Simultaneous perturbation learning rule for recurrent neural networks and its FPGA implementation
IEEE Transactions on Neural Networks
A new architecture for digital stochastic pulse-mode neurons based on the voting circuit
IEEE Transactions on Neural Networks
FPGA-based real-time implementation of an adaptive RCMAC control system
WSEAS Transactions on Circuits and Systems
Image contrast enhancement using morphological decomposition by reconstruction
WSEAS Transactions on Circuits and Systems
Hi-index | 0.00 |
In this paper, we present FPGA recurrent neural network systems with learning capability using the simultaneous perturbation learning rule. In the neural network systems, outputs and internal values are represented by pulse train. That is, analog recurrent neural networks with pulse frequency representation are considered. The pulse density representation and the simultaneous perturbation enable the systems with learning capability to easily implement as a hardware system. As typical examples of the recurrent neural networks, Hopfield neural network and the bidirectional associative memory are considered. Details of the systems and the circuit design are described. Analog and digital examples for these Hopfield neural network and the bidirectional associative memory are also shown to confirm a viability of the system configuration and the learning capability.