Simbrain is a tool for building artificial neural networks that has been developed with the philosophy of ease-of-use and intuitive design. We encourage you to simply launch Simbrain and experiment. For a guided dive directly into Simbrain, try this quickstart. For in-depth documentation on each Simbrain component, follow the links below. Simbrain is open source and uses the GNU license.

Workspace

The Simbrain workspace is the encompassing framework which contains all simulation components: networks, worlds, and gauges.

Networks

The network component of Simbrain represents a simulated neural circuit. Networks are the core component of a Simbrain simulation. They are built using a simple graphical interface.

Worlds

Worlds are components that interact with Network components by giving and/or receiving information. The "OdorWorld" shown to the right simulates a creature's ability to move and smell in a simple two-dimensional world.

Gauges

The states that occur in a neural network correspond to points in a high dimensional space. These states and the patterns they form can be visually inspected using the gauge components. This allows for visual analysis of the representational structures that develop in a neural network.

 

Credits

Simbrain was designed and created by Jeff Yoshimi. Team members include Kyle Baron, Ryan Bartley, Cheryl Evry, John Ewart, Michael Heuer, Scott Hotton, Jason Laurel, Ricardo Velasco, and William Benjamin St. Clair. Art and design: David Fleischmann, Brian Nucum, and Elizabeth Reagh of Goodform Design.Thanks also to Matthew Lloyd, Simon Levy, the Piccolo users group, and Mai Ngoc Thang. This software uses the Piccolo, Castor, SNARLI, and JAMA libraries. The development of this work was supported by a grant from the William and Flora Hewlett Foundation.