Multi-Layer Perceptron Classifier

../../../../_images/neuralnetwork.svg

Multi-layer perceptron classifier

Configuration:

  • max_iter

    Maximum number of iterations. The solver iterates until convergence (determined by ‘tol’) or this number of iterations. For stochastic solvers (‘sgd’, ‘adam’), note that this determines the number of epochs (how many times each data point will be used), not the number of gradient steps.

  • hidden_layer_sizes

    The ith element represents the number of neurons in the ith hidden layer.

  • activation

    Activation function for the hidden layer.

    • ‘identity’, no-op activation, useful to implement linear bottleneck, returns f(x) = x
    • ‘logistic’, the logistic sigmoid function, returns f(x) = 1 / (1 + exp(-x)).
    • ‘tanh’, the hyperbolic tan function, returns f(x) = tanh(x).
    • ‘relu’, the rectified linear unit function, returns f(x) = max(0, x)
  • solver

    The solver for weight optimization.

    • ‘lbfgs’ is an optimizer in the family of quasi-Newton methods.
    • ‘sgd’ refers to stochastic gradient descent.
    • ‘adam’ refers to a stochastic gradient-based optimizer proposed by Kingma, Diederik, and Jimmy Ba

    Note: The default solver ‘adam’ works pretty well on relatively large datasets (with thousands of training samples or more) in terms of both training time and validation score. For small datasets, however, ‘lbfgs’ can converge faster and perform better.

  • batch_size

    Size of minibatches for stochastic optimizers. If the solver is ‘lbfgs’, the classifier will not use minibatch. When set to “auto”, batch_size=min(200, n_samples)

  • learning_rate

    Learning rate schedule for weight updates.

    • ‘constant’ is a constant learning rate given by ‘learning_rate_init’.
    • ‘invscaling’ gradually decreases the learning rate at each time step ‘t’ using an inverse scaling exponent of ‘power_t’. effective_learning_rate = learning_rate_init / pow(t, power_t)
    • ‘adaptive’ keeps the learning rate constant to ‘learning_rate_init’ as long as training loss keeps decreasing. Each time two consecutive epochs fail to decrease training loss by at least tol, or fail to increase validation score by at least tol if ‘early_stopping’ is on, the current learning rate is divided by 5.

    Only used when solver='sgd'.

  • shuffle

    Whether to shuffle samples in each iteration. Only used when solver=’sgd’ or ‘adam’.

  • early_stopping

    Whether to use early stopping to terminate training when validation score is not improving. If set to true, it will automatically set aside 10% of training data as validation and terminate training when validation score is not improving by at least tol for n_iter_no_change consecutive epochs. Only effective when solver=’sgd’ or ‘adam’

  • validation_fraction

    The proportion of training data to set aside as validation set for early stopping. Must be between 0 and 1. Only used if early_stopping is True

  • alpha

    L2 penalty (regularization term) parameter.

  • tol

    Tolerance for the optimization. When the loss or score is not improving by at least tol for n_iter_no_change consecutive iterations, unless learning_rate is set to ‘adaptive’, convergence is considered to be reached and training stops.

  • learning_rate_init

    The initial learning rate used. It controls the step-size in updating the weights. Only used when solver=’sgd’ or ‘adam’.

  • power_t

    The exponent for inverse scaling learning rate. It is used in updating effective learning rate when the learning_rate is set to ‘invscaling’. Only used when solver=’sgd’.

  • momentum

    Momentum for gradient descent update. Should be between 0 and 1. Only used when solver=’sgd’.

  • nesterovs_momentum

    Whether to use Nesterov’s momentum. Only used when solver=’sgd’ and momentum > 0.

  • beta_1

    Exponential decay rate for estimates of first moment vector in adam, should be in [0, 1). Only used when solver=’adam’

  • beta_2

    Exponential decay rate for estimates of second moment vector in adam, should be in [0, 1). Only used when solver=’adam’

  • epsilon

    Value for numerical stability in adam. Only used when solver=’adam’

  • random_state

    If int, random_state is the seed used by the random number generator; If RandomState instance, random_state is the random number generator; If None, the random number generator is the RandomState instance used by np.random.

  • warm_start

    When set to True, reuse the solution of the previous call to fit as initialization, otherwise, just erase the previous solution. See warm_start.

Attributes:

  • classes_

    Class labels for each output.

  • loss_

    The current loss computed with the loss function.

  • coefs_

    The ith element in the list represents the weight matrix corresponding to layer i.

  • intercepts_

    The ith element in the list represents the bias vector corresponding to layer i + 1.

  • n_iter_

    The number of iterations the solver has ran.

  • n_layers_

    Number of layers.

  • n_outputs_

    Number of outputs.

  • out_activation_

    Name of the output activation function.

Input ports:

Output ports:
model : model
Model
max_iter (max_iter)
Maximum number of iterations. The solver iterates until convergence (determined by ‘tol’) or this number of iterations. For stochastic solvers (‘sgd’, ‘adam’), note that this determines the number of epochs (how many times each data point will be used), not the number of gradient steps.
hidden_layer_sizes (hidden_layer_sizes)
The ith element represents the number of neurons in the ith hidden layer.
activation (activation)

Activation function for the hidden layer.

  • ‘identity’, no-op activation, useful to implement linear bottleneck, returns f(x) = x
  • ‘logistic’, the logistic sigmoid function, returns f(x) = 1 / (1 + exp(-x)).
  • ‘tanh’, the hyperbolic tan function, returns f(x) = tanh(x).
  • ‘relu’, the rectified linear unit function, returns f(x) = max(0, x)
solver (solver)

The solver for weight optimization.

  • ‘lbfgs’ is an optimizer in the family of quasi-Newton methods.
  • ‘sgd’ refers to stochastic gradient descent.
  • ‘adam’ refers to a stochastic gradient-based optimizer proposed by Kingma, Diederik, and Jimmy Ba

Note: The default solver ‘adam’ works pretty well on relatively large datasets (with thousands of training samples or more) in terms of both training time and validation score. For small datasets, however, ‘lbfgs’ can converge faster and perform better.

batch_size (batch_size)
Size of minibatches for stochastic optimizers. If the solver is ‘lbfgs’, the classifier will not use minibatch. When set to “auto”, batch_size=min(200, n_samples)
learning_rate (learning_rate)

Learning rate schedule for weight updates.

  • ‘constant’ is a constant learning rate given by ‘learning_rate_init’.
  • ‘invscaling’ gradually decreases the learning rate at each time step ‘t’ using an inverse scaling exponent of ‘power_t’. effective_learning_rate = learning_rate_init / pow(t, power_t)
  • ‘adaptive’ keeps the learning rate constant to ‘learning_rate_init’ as long as training loss keeps decreasing. Each time two consecutive epochs fail to decrease training loss by at least tol, or fail to increase validation score by at least tol if ‘early_stopping’ is on, the current learning rate is divided by 5.

Only used when solver='sgd'.

shuffle (shuffle)
Whether to shuffle samples in each iteration. Only used when solver=’sgd’ or ‘adam’.
early_stopping (early_stopping)
Whether to use early stopping to terminate training when validation score is not improving. If set to true, it will automatically set aside 10% of training data as validation and terminate training when validation score is not improving by at least tol for n_iter_no_change consecutive epochs. Only effective when solver=’sgd’ or ‘adam’
validation_fraction (validation_fraction)
The proportion of training data to set aside as validation set for early stopping. Must be between 0 and 1. Only used if early_stopping is True
alpha (alpha)
L2 penalty (regularization term) parameter.
tol (tol)
Tolerance for the optimization. When the loss or score is not improving by at least tol for n_iter_no_change consecutive iterations, unless learning_rate is set to ‘adaptive’, convergence is considered to be reached and training stops.
learning_rate_init (learning_rate_init)
The initial learning rate used. It controls the step-size in updating the weights. Only used when solver=’sgd’ or ‘adam’.
power_t (power_t)
The exponent for inverse scaling learning rate. It is used in updating effective learning rate when the learning_rate is set to ‘invscaling’. Only used when solver=’sgd’.
momentum (momentum)
Momentum for gradient descent update. Should be between 0 and 1. Only used when solver=’sgd’.
nesterovs_momentum (nesterovs_momentum)
Whether to use Nesterov’s momentum. Only used when solver=’sgd’ and momentum > 0.
beta_1 (beta_1)
Exponential decay rate for estimates of first moment vector in adam, should be in [0, 1). Only used when solver=’adam’
beta_2 (beta_2)
Exponential decay rate for estimates of second moment vector in adam, should be in [0, 1). Only used when solver=’adam’
epsilon (epsilon)
Value for numerical stability in adam. Only used when solver=’adam’
random_state (random_state)
If int, random_state is the seed used by the random number generator; If RandomState instance, random_state is the random number generator; If None, the random number generator is the RandomState instance used by np.random.
warm_start (warm_start)
When set to True, reuse the solution of the previous call to fit as initialization, otherwise, just erase the previous solution. See warm_start.

Some of the docstrings for this module have been automatically extracted from the scikit-learn library and are covered by their respective licenses.

class node_MLPClassifier.MLPClassifier[source]