Be the first to post a text review of Python Neural Genetic Algorithm Hybrids. Rate and review a project by clicking thumbs up or thumbs down in the right column.

• PyNeurgen: 0.2 Released

  A new version of PyNeurGen has been released with more features for recurrent networks. PyNeurGen is a set of Python tools for creating neural networks, genetic algorithms/genetic programming, and hybrids of both. Grammatical evolution is the form of evolutionary computation. The supported features for neural networks include MLP, backpropagation, recurrent, sparse, and skip-layer networks. This latest version, PyNeurGen-0.2 provides a more convenient means for creating recurrent networks, including Elman, Jordan, NARX, and user specified blends. A more detailed description of features can be found at http://pyneurgen.sourceforge.net Instructions for making various kinds of network structures can be found at http://pyneurgen.sourceforge.net/recurrent.html PyNeurGen can be downloaded from SourceForge.net at: http://sourceforge.net/project/showfiles.php?group_id=223791

  posted by sidorof 518 days ago

• File released: /pyneurgen/pyneurgen-0.2/pyneurgen-0.2.zip

  posted 521 days ago

• File released: /pyneurgen/pyneurgen-0.2/pyneurgen-0.2.tar.gz

  posted 521 days ago

• pyneurgen pyneurgen-0.2 file released: pyneurgen-0.2.zip

  Pyneurgen: Python Neural Genetic Hybrids Change Log ======================================== Check http://pyneurgen.sourceforge.net for the latest documentation. pyneurgen-0.2 Updates primarily related to recurrent networks. In attempt to enable an easier use of recurrent features, a new set of classes has been implemented. NeuralNet.init_layers no longer takes copy_levels as a parameter. Rather, it accepts along with the number of nodes for input, hidden and output layers, classes derived from a class called RecurrentConfig, which modifies the network structure to embody recurrence. Using the feature, a class such as JordanRecurrent, ElmanSimpleRecurrent, or NARXRecurrent can be passed in and the appropriate structure configured. The RecurrentConfig class can easily be subclassed for other custom types. As before, the copy nodes can be easily be added manually to network structures to achieve other kinds of structures. CopyNode now has some additional features to enable the above classes. In the prior version, the Copy node value was always replaced by the source node value. Now, a weighting system of existing_weight and incoming weight is used to modify the incoming values and/or retain part of the existing value. For flexibility, the copy node can take the source node's value, or activation, and have its activation type, independent of the source node's activation. Test modules are slightly more complete. pyneurgen-0.1 Initial version

  posted 521 days ago

• pyneurgen pyneurgen-0.2 file released: pyneurgen-0.2.tar.gz

  Pyneurgen: Python Neural Genetic Hybrids Change Log ======================================== Check http://pyneurgen.sourceforge.net for the latest documentation. pyneurgen-0.2 Updates primarily related to recurrent networks. In attempt to enable an easier use of recurrent features, a new set of classes has been implemented. NeuralNet.init_layers no longer takes copy_levels as a parameter. Rather, it accepts along with the number of nodes for input, hidden and output layers, classes derived from a class called RecurrentConfig, which modifies the network structure to embody recurrence. Using the feature, a class such as JordanRecurrent, ElmanSimpleRecurrent, or NARXRecurrent can be passed in and the appropriate structure configured. The RecurrentConfig class can easily be subclassed for other custom types. As before, the copy nodes can be easily be added manually to network structures to achieve other kinds of structures. CopyNode now has some additional features to enable the above classes. In the prior version, the Copy node value was always replaced by the source node value. Now, a weighting system of existing_weight and incoming weight is used to modify the incoming values and/or retain part of the existing value. For flexibility, the copy node can take the source node's value, or activation, and have its activation type, independent of the source node's activation. Test modules are slightly more complete. pyneurgen-0.1 Initial version

  posted 521 days ago

• pyneurgen pyneurgen-0.1.tar.gz file released: pyneurgen-0.1.tar.gz

  Change Log ======================================== pyneurgen-0.1 Initial version

  posted 535 days ago

• File released: /pyneurgen/pyneurgen-0.1.tar.gz/pyneurgen-0.1.tar.gz

  posted 535 days ago