From emergent
Jump to: navigation, search
Crystal Clear app display.png Using emergent

Tutorials for Emergent

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

Emergent Logo
Main User Docs

Video tutorials

Build a standard network Construct your own network Creating a control panel Assigning Unit Names
Creating Monitor Vars and Graphs Creating Child Specs Creating a CycleMonitor Creating a Scalar Value Layer
play-icon.png How to build your own network --Needs to be updated!
play-icon.png How to run emergent from the command line
play-icon.png Visualization features --Needs to be updated!
play-icon.png Test Screencast --Sandbox for uploading tutorials - for testing only!

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.
  • Data Processing Tutorial -- data processing tutorial for DataTables -- covers the basic operations that you can do with data tables, which are central to much of emergent
  • Backpropagation Tutorial (incomplete!)-- construct a feed-forward backpropagation (backward propagation of errors, Bp in emergent shorthand) 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)
  • Network Data Tutorial -- How to gather data on various aspects of network function (success, activity levels, etc) and process these appropriately for different conditions. Expands on the basic data gathering in the AX tutorial, but starts from the basics.

Multi-Media Input/Outputs

  • ImageProc Tutorial -- image processing tutorial -- how to configure a network and Programs to operate on bitmap images.
  • AudioProc Tutorial -- audio processing tutorial -- how to configure a network and Programs to operate on audio inputs.

Complex Network Structures

  • SRN Tutorial -- how to construct a simple recurrent network.
  • TD Tutorial -- constructing a Temporal Differences model in Leabra.
  • PVLV Tutorial -- constructing a PVLV (Primary Value, Learned Value Pavlovian conditioning) model in Leabra.
  • PBWM Tutorial -- constructing a Prefrontal-cortex Basal-ganglia Working Memory (PBWM) model in Leabra.
  • Network Access Tutorial -- Examples on how to access and set various network variables and parameters programmatically