Aquila 2.0 prealpha
Cognitive Robotics Architecture
This Aquila-compliant module trains self-organising maps
Launch this module with –help parameter to see the list of possible options
Needs a training file, which can be set from:
By default, trained self-organising map is saved to 'som.txt' file. This can be changed from:
Default values for various paramters are loaded from a configuration file, which can be modified in /conf/config.ini
The file consists in a few sections:
output - output file used for saving trained self-organising map maxThreads 256 - maximum number of GPU threads per block learningRate 0.1 - learning rate used druing the training sigma 0.0 - sigma parameters that changes the training mode if set to a non-zero value numSubIterations - number of sub-iterations numOutputs - number of self-organising map outputs
Linux, OSX and Windows.
This will launch the training on the third GPU on the system (Id=2) for 1000 iterations reading training data from the colour.txt file that can be found in /example folder.
selfOrganisingMap –input colour.txt –iterations 1000 –gpu 2