Package mdp :: Package nodes
[hide private]
[frames] | no frames]

Package nodes

Classes [hide private]
  AdaptiveCutoffNode
Node which uses the data history during training to learn cutoff values.
  Convolution2DNode
Convolve input data with filter banks.
  CuBICANode
Perform Independent Component Analysis using the CuBICA algorithm.
  CutoffNode
Node to cut off values at specified bounds.
  DiscreteHopfieldClassifier
Node for simulating a simple discrete Hopfield model
  EtaComputerNode
Compute the eta values of the normalized training data.
  FANode
Perform Factor Analysis.
  FDANode
Perform a (generalized) Fisher Discriminant Analysis of its input.
  FastICANode
Perform Independent Component Analysis using the FastICA algorithm.
  GaussianClassifier
Perform a supervised Gaussian classification.
  GeneralExpansionNode
Expands the input samples by applying to them one or more functions provided.
  GrowingNeuralGasExpansionNode
Perform a trainable radial basis expansion, where the centers and sizes of the basis functions are learned through a growing neural gas.
  GrowingNeuralGasNode
Learn the topological structure of the input data by building a corresponding graph approximation.
  HLLENode
Perform a Hessian Locally Linear Embedding analysis on the data.
  HistogramNode
Node which stores a history of the data during its training phase.
  HitParadeNode
Collect the first ``n`` local maxima and minima of the training signal which are separated by a minimum gap ``d``.
  ICANode
ICANode is a general class to handle different batch-mode algorithm for Independent Component Analysis.
  ISFANode
Perform Independent Slow Feature Analysis on the input data.
  IdentityNode
Execute returns the input data and the node is not trainable.
  JADENode
Perform Independent Component Analysis using the JADE algorithm.
  KMeansClassifier
Employs K-Means Clustering for a given number of centroids.
  KNNClassifier
K-Nearest-Neighbour Classifier.
  LLENode
Perform a Locally Linear Embedding analysis on the data.
  LibSVMClassifier
The ``LibSVMClassifier`` class acts as a wrapper around the LibSVM library for support vector machines.
  LinearRegressionNode
Compute least-square, multivariate linear regression on the input data, i.e., learn coefficients ``b_j`` so that::
  NIPALSNode
Perform Principal Component Analysis using the NIPALS algorithm.
  NearestMeanClassifier
Nearest-Mean classifier.
  NeuralGasNode
Learn the topological structure of the input data by building a corresponding graph approximation (original Neural Gas algorithm).
  NoiseNode
Inject multiplicative or additive noise into the input data.
  NormalNoiseNode
Special version of ``NoiseNode`` for Gaussian additive noise.
  NormalizeNode
Make input signal meanfree and unit variance
  PCANode
Filter the input data through the most significatives of its principal components.
  PerceptronClassifier
A simple perceptron with input_dim input nodes.
  PolynomialExpansionNode
Perform expansion in a polynomial space.
  QuadraticExpansionNode
Perform expansion in the space formed by all linear and quadratic monomials.
  RBFExpansionNode
Expand input space with Gaussian Radial Basis Functions (RBFs).
  RBMNode
Restricted Boltzmann Machine node.
  RBMWithLabelsNode
Restricted Boltzmann Machine with softmax labels.
  SFA2Node
Get an input signal, expand it in the space of inhomogeneous polynomials of degree 2 and extract its slowly varying components.
  SFANode
Extract the slowly varying components from the input data.
  SignumClassifier
This classifier node classifies as ``1`` if the sum of the data points...
  SimpleMarkovClassifier
A simple version of a Markov classifier.
  TDSEPNode
Perform Independent Component Analysis using the TDSEP algorithm.
  TimeDelayNode
Copy delayed version of the input signal on the space dimensions.
  TimeDelaySlidingWindowNode
``TimeDelaySlidingWindowNode`` is an alternative to ``TimeDelayNode`` which should be used for online learning/execution.
  TimeFramesNode
Copy delayed version of the input signal on the space dimensions.
  WhiteningNode
*Whiten* the input data by filtering it through the most significatives of its principal components.
  XSFANode
Perform Non-linear Blind Source Separation using Slow Feature Analysis.
  _OneDimensionalHitParade
Class to produce hit-parades (i.e., a list of the largest and smallest values) out of a one-dimensional time-series.
Functions [hide private]
 
_expanded_dim(degree, nvariables)
Return the size of a vector of dimension ``nvariables`` after a polynomial expansion of degree ``degree``.
Variables [hide private]
  __package__ = 'mdp.nodes'
Function Details [hide private]

_expanded_dim(degree, nvariables)

 
Return the size of a vector of dimension ``nvariables`` after
a polynomial expansion of degree ``degree``.


Variables Details [hide private]

__package__

Value:
'mdp.nodes'