Amygdala spiking neural network Amygdala is an AI Foundry member project
Home
Understanding Amygdala
What are SNNs?
What is Amygdala?
Demonstrations
Frequently-asked questions
Supporting research
Advanced features
Distributed operation
Network evolution (GA)
GUI network editor
Using Amygdala
Platforms supported
Download & install
Documentation
Sample networks
Bugs & feedback
The future of Amygdala
Roadmap for development
Getting involved
Contacts
Development site

 

Understanding Amygdala : Demonstrations
  • Spikeloop (MPEG - 1.4MB): The "Hello World" application of recurrent spiking neural networks. The network's topology comprises a number of layers, each one fully connected to the next. The last layer (red) is connected to the first again to close the loop. The loop is triggered by a one time spiking of the input neurons (blue). This forms a spike front that rotates indefinitelly.
  • Liquid State machine (MPEG - 2.7MB) consisting of 680 neurons and 6360 synapses. This piece of magic cirquitry recently got devised by Maass, Nattschläger and Markram in this paper There is also a still picture including all synaptic connections (1280x1024) and a more traditional diagram. Neuron ID 1-40 are input neurons (blue) and are externally triggered in a random time series.
  • Network debugger and visualizer (396KB): A precompiled demo running the spikeloop and mouse samples in the openGL-based network visualizer.
Hosted by
SourceForge.net
Amygdala : spiking neural network Site last updated: Feb 28, 2003
Send feedback about this site