From Emergent

Contents 1 Tutorials for Emergent 1.1 Core Stuff: Networks, DataTables and Programs 1.2 Multi-Media Input/Outputs 1.3 Complex Network Structures

Tutorials for Emergent

IMPORTANT NOTE: many of these tutorials do not yet exist unfortunately -- that is not a bug in your browser. Contributions welcome!

Core Stuff: Networks, DataTables and Programs

• Build your own network -- constructing a basic 3-layer network using the wizard, and training it on a pre-defined (small) set of training patterns.

• AX_Tutorial -- construct a simple model of an actual psychological task (the CPT-AX task), from start to finish. This one tutorial touches on all major aspects of the system. It is available as an interactive emergent project in demo/leabra/ax_tutorial.proj (just run emergent, open the project and start following the instructions that appear), and in the wiki.

• VisSearchTutorial -- constructing a simple visual search network, focusing on a simple Program for creating the training environment using multi-dimensional matrix operations in a DataTable

• DataProcTutorial -- data processing tutorial for DataTables -- covers the basic operations that you can do with data tables, which are central to much of Emergent

• DataAnalTutorial -- data analysis tutorial -- creates a Program for analyzing the number of epochs required to train a network -- covers graphing.

• Bp_Tutorial -- construct a feed-forward back-propagation neural net model on a sample data set. This tutorial covers the following topics: an outline of a Bp network and its learning algorithms, setting up a Bp project, constructing a multi-layer Bp network with a single output variable, setting up data training and testing data tables, populating data tables by importing data from a file, setting up data tables and variables to contain train and test output data, setting up two sets of control programs (one to train the network and one to test additional data on the trained network)

Multi-Media Input/Outputs

• ImageProcTutorial -- image processing tutorial -- how to configure a network and Programs to operate on bitmap images.

• AudioProcTutorial -- audio processing tutorial -- how to configure a network and Programs to operate on audio inputs.

Complex Network Structures

• SRNTutorial -- how to construct a simple recurrent network.

• TDTutorial -- constructing a Temporal Differences model in Leabra.

• PVLVTutorial -- constructing a PVLV (Primary Value, Learned Value Pavlovian conditioning) model in Leabra.

• PBWMTutorial -- constructing a Prefrontal-cortex Basal-ganglia Working Memory (PBWM) model in Leabra.