Package ML :: Package Neural :: Module Network :: Class Network

Class Network

a neural network

Instance Methods

[hide private]

ConstructRandomWeights(self, minWeight=-1, maxWeight=1)
initialize all the weights in the network to random numbers **Arguments** - minWeight: the minimum value a weight can take - maxWeight: the maximum value a weight can take **Note** random numbers are assigned using _Numeric_'s _RandomArray_ module, so if you want to be seeding the generators, be sure to hit that one too.

source code

FullyConnectNodes(self)
Fully connects each layer in the network to the one above it...

source code

ConstructNodes(self, nodeCounts, actFunc, actFuncParms)
build an unconnected network and set node counts **Arguments** - nodeCounts: a list containing the number of nodes to be in each layer.

source code

GetInputNodeList(self)
returns a list of input node indices...

source code

GetOutputNodeList(self)
returns a list of output node indices...

source code

GetHiddenLayerNodeList(self, which)
returns a list of hidden nodes in the specified layer...

source code

GetNumNodes(self)
returns the total number of nodes...

source code

GetNumHidden(self)
returns the number of hidden layers...

source code

GetNode(self, which)
returns a particular node...

source code

GetAllNodes(self)
returns a list of all nodes...

source code

ClassifyExample(self, example, appendExamples=0)
classifies a given example and returns the results of the output layer.

source code

GetLastOutputs(self)
returns the complete list of output layer values from the last time this node classified anything

source code

__str__(self)
provides a string representation of the network

source code

__init__(self, nodeCounts, nodeConnections=None, actFunc=<class 'ML.Neural.ActFuncs.Sigmoid'>, actFuncParms=(), weightBounds=1)
Constructor This constructs and initializes the network based upon the specified node counts. source code

Method Details

[hide private]

FullyConnectNodes(self)

source code

Fully connects each layer in the network to the one above it


**Note**
  this sets the connections, but does not assign weights

ConstructNodes(self, nodeCounts, actFunc, actFuncParms)

source code

build an unconnected network and set node counts

**Arguments**

  - nodeCounts: a list containing the number of nodes to be in each layer.
     the ordering is:
      (nInput,nHidden1,nHidden2, ... , nHiddenN, nOutput)

GetInputNodeList(self)

source code

returns a list of input node indices

GetOutputNodeList(self)

source code

returns a list of output node indices

GetHiddenLayerNodeList(self, which)

source code

returns a list of hidden nodes in the specified layer

GetNumNodes(self)

source code

returns the total number of nodes

GetNumHidden(self)

source code

returns the number of hidden layers

GetNode(self, which)

source code

returns a particular node

GetAllNodes(self)

source code

returns a list of all nodes

ClassifyExample(self, example, appendExamples=0)

source code

classifies a given example and returns the results of the output layer.

**Arguments**

  - example: the example to be classified

**NOTE:**

  if the output layer is only one element long,
  a scalar (not a list) will be returned.  This is why a lot of the other
  network code claims to only support single valued outputs.

init(self, nodeCounts, nodeConnections=None, actFunc=<class 'ML.Neural.ActFuncs.Sigmoid'>, actFuncParms=`()`, weightBounds=1)
(Constructor)

source code

Constructor

This constructs and initializes the network based upon the specified
node counts.

A fully connected network with random weights is constructed.

**Arguments**

  - nodeCounts: a list containing the number of nodes to be in each layer.
     the ordering is:
      (nInput,nHidden1,nHidden2, ... , nHiddenN, nOutput)

  - nodeConnections: I don't know why this is here, but it's optional.  ;-)

  - actFunc: the activation function to be used here.  Must support the API
      of _ActFuncs.ActFunc_.

  - actFuncParms: a tuple of extra arguments to be passed to the activation function
      constructor.

  - weightBounds:  a float which provides the boundary on the random initial weights

Class Network

FullyConnectNodes(self)

ConstructNodes(self, nodeCounts, actFunc, actFuncParms)

GetInputNodeList(self)

GetOutputNodeList(self)

GetHiddenLayerNodeList(self, which)

GetNumNodes(self)

GetNumHidden(self)

GetNode(self, which)

GetAllNodes(self)

ClassifyExample(self, example, appendExamples=0)

__init__(self, nodeCounts, nodeConnections=None, actFunc=<class 'ML.Neural.ActFuncs.Sigmoid'>, actFuncParms=(), weightBounds=1) (Constructor)

init(self, nodeCounts, nodeConnections=None, actFunc=<class 'ML.Neural.ActFuncs.Sigmoid'>, actFuncParms=`()`, weightBounds=1)
(Constructor)