Generalization and Selection of Examples in Feedforward Neural Networks
Neural Computation
Constructive threshold logic addition: a synopsis of the last decade
ICANN/ICONIP'03 Proceedings of the 2003 joint international conference on Artificial neural networks and neural information processing
Hi-index | 0.01 |
A feedforward layered neural network (perceptron) with onehidden layer, which adds two N-bit binary numbers isconstructed. The set of synaptic strengths and thresholds isobtained exactly for different architectures of the network and forarbitrary N. These structures can be easily generalized toperform more complicated arithmetic operations (likesubtraction).