Neural Network Framework 1.1.3 (Default branch)


 
Thread Tools Search this Thread
Special Forums News, Links, Events and Announcements Software Releases - RSS News Neural Network Framework 1.1.3 (Default branch)
# 1  
Old 05-13-2008
Neural Network Framework 1.1.3 (Default branch)

Neural Network Framework is a C++ framework to develop, simulate, and analyze arbitrary complex neural networks. The programmer can use the classes provided to create neural networks with arbitrary topology and mixed type of neurons. It's very easy to add customized neurons and layers. License: GNU General Public License (GPL) Changes:
Saving of RealMat matrices on XML has been made prettier. Two activation functions were added: GainFunction and LogLikeFunction. A skipList parameter were added to the saveXML function in order to allow choosing of which tag to skip during saving.Image

More...
Login or Register to Ask a Question

Previous Thread | Next Thread
Login or Register to Ask a Question
FANN_SET_ACTIVATION_STEEPNESS(3)					 1					  FANN_SET_ACTIVATION_STEEPNESS(3)

fann_set_activation_steepness - Sets the activation steepness for supplied neuron and layer number

SYNOPSIS
bool fann_set_activation_steepness (resource $ann, float $activation_steepness, int $layer, int $neuron) DESCRIPTION
Set the activation steepness for neuron number neuron in layer number layer, counting the input layer as layer 0. It is not possible to set activation steepness for the neurons in the input layer. The steepness of an activation function says something about how fast the activation function goes from the minimum to the maximum. A high value for the activation function will also give a more agressive training. When training neural networks where the output values should be at the extremes (usually 0 and 1, depending on the activation function), a steep activation function can be used (e.g. 1.0). The default activation steepness is 0.5. PARAMETERS
o $ann -Neural network resource. o $activation_steepness - The activation steepness. o $layer - Layer number. o $neuron - Neuron number. RETURN VALUES
Returns TRUE on success, or FALSE otherwise. SEE ALSO
fann_set_activation_steepness_layer(3), fann_set_activation_steepness_hidden(3), fann_set_activation_steepness_output(3), fann_get_activa- tion_steepness(3), fann_set_activation_function(3). PHP Documentation Group FANN_SET_ACTIVATION_STEEPNESS(3)