Neuron class
Neuron class provides LNU (Linear Neural Unit), QNU (Quadratic Neural Unit), RBF (Radial Basis Function), MLP (Multi Layer Perceptron), MLP-ELM (Multi Layer Perceptron - Extreme Learning Machine) neurons learned with Gradient descent or LeLevenberg–Marquardt algorithm. This class is suitable for prediction on time series.
Dependencies
Neuron class needs pandas and numpy to work propertly.
Example of usage
Consider Y are targets and X are inputs.
## LNUGD
neuron = LNUGD()
prediction = 1
yn, w, e, Wall, MSE = neuron.train(Y_train, X_train, epochs=2, prediction=prediction)
yn, w, Wall, MSE, e = neuron.countSerie(Y, X, logging=False, prediction=prediction)
QNULM
neuron = QNULM()
prediction = 1
yn, w, e, Wall, MSE = neuron.train(Y_train, X_train, epochs=10, prediction=prediction)
yn, w, MSE, e = neuron.countSerie(Y, X, logging=False, prediction=prediction)
RBF
neuron = RBF()
prediction = 1
neuron.train(Y_train, X_train, prediction=prediction)
yn = neuron.count(Y,X, logging=True, beta=0.01, prediction=prediction)
MLPGD
neuron = MLPGD()
prediction = 1
yn = neuron.count(Y_train, X_train, prediction=prediction, epochs=5)
yn = neuron.count(Y, X, prediction=prediction, epochs=1)
MLPELM
neuron = MLPELM()
prediction = 1
yn = neuron.count(Y_train, X_train, prediction = prediction, epochs = 10)
yn = neuron.count(Y, X, prediction = prediction)
MLPLMWL
neuron = MLPLMWL()
prediction = 1
yn = neuron.count(Y, X, learningWindow = 50, overLearn = 10, prediction = prediction)
Support me
If you find this useful, consider supporting independent open-source development and buy me a coffee.
3 Sep 16, 2022
28 Jan 04, 2023
87 Dec 28, 2022
90 Dec 26, 2022
3 Dec 19, 2022
14 Nov 29, 2022
113 Dec 14, 2022
5 Nov 25, 2022
7 Aug 23, 2022
410 Jan 03, 2023
9 Jul 31, 2022
3 Jun 03, 2021
345 Jan 08, 2023
143 Dec 24, 2022
119 Jan 01, 2023
195 Dec 30, 2022
3.9k Jan 02, 2023
2 Feb 09, 2022
3.2k Jan 08, 2023
192 Dec 20, 2022