fynance.models.neural_network.MultiLayerPerceptron¶
-
class
fynance.models.neural_network.
MultiLayerPerceptron
(X, y, layers=[], activation=None, drop=None, x_type=None, y_type=None, bias=True, activation_kwargs={})¶ Neural network with MultiLayer Perceptron architecture.
Refered as vanilla neural network model, with n hidden layers s.t n \(\geq\) 1, with each one a specified number of neurons.
Parameters: - X, y : array-like or int
- If it’s an array-like, respectively inputs and outputs data.
- If it’s an integer, respectively dimension of inputs and outputs.
- layers : list of int
List of number of neurons in each hidden layer.
- activation : torch.nn.Module
Activation function of layers.
- drop : float, optional
Probability of an element to be zeroed.
See also
BaseNeuralNet
,RollMultiLayerPerceptron
Attributes: - criterion : torch.nn.modules.loss
A loss function.
- optimizer : torch.optim
An optimizer algorithm.
- n : int
Number of hidden layers.
- layers : list of int
List with the number of neurons for each hidden layer.
- f : torch.nn.Module
Activation function.
Methods
set_optimizer
(criterion, optimizer[, params])Set the optimizer object. train_on
(X, y)Trains the neural network model. predict
(X)Predicts outputs of neural network model. set_data
(X, y[, x_type, y_type])Set data inputs and outputs.