Learning algorithms for a specific configuration of the quantron
2011
The quantron is a new artificial neuron model, able to solve nonlinear classification problems, for which an efficient learning algorithm has yet to be developed. Using surrogate potentials, constraints on some parameters and an infinite number of potentials, we obtain analytical expressions involving ceiling functions for the activation function of the quantron. We then show how to retrieve the parameters of a neuron from the images it produced.
Keywords:
- Machine learning
- Backpropagation
- Supervised learning
- Expression (mathematics)
- Pattern recognition
- Artificial intelligence
- Artificial neural network
- Multilayer perceptron
- Nonlinear system
- Algorithm
- Activation function
- Computer science
- Artificial neuron
- nonlinear classification
- infinite number
- analytical expressions
- Correction
- Source
- Cite
- Save
- Machine Reading By IdeaReader
9
References
1
Citations
NaN
KQI