A new neural network architecture based on quadratic function neurons
1991
In this paper, a class of multilayer perceptrons known as rotational quadratic function neural networks (RQFNN) is introduced. The rotational quadratic function neuron (RQFN), at the center of this class of networks, is a particular implementation of the quadratic function neuron (QFN). Compared with the traditional implementation, the RQFN requires much less fan-ins and thus much smaller cross-connection volume. The economy of the fan-ins and the cross connection volumes facilitates the mapping of the model onto silicon. >
Keywords:
- Types of artificial neural networks
- Feedforward neural network
- Mathematical optimization
- Physical neural network
- Winner-take-all
- Machine learning
- Quadratic function
- Multilayer perceptron
- Rectifier (neural networks)
- Activation function
- Computer science
- Artificial intelligence
- Topology
- Time delay neural network
- Theoretical computer science
- Correction
- Source
- Cite
- Save
- Machine Reading By IdeaReader
7
References
0
Citations
NaN
KQI