ASpiReNN stands for Artificial SPIking REcurrent Neural Network. ASpiReNN is a little library written in C which, as its name suggests, allows to simulates artificial spiking (or not) recurrent (or not) neural networks.
Product's homepage
Here are some key features of "ASpiReNN":
· leaky integrate-and-fire support
· possibility to add new neuron types
· Spike-Timing Dependent Plasticity learning rule
· possibility to add new learning rules
· fast multilayer networks
· best suited for highly recurrent neural nets
· Python bindings
Requirements:
· A C99 compatible compiler (such as GCC)
· ... and that should be enough, theoretically. In pratice it will be easier to install on an Unix platform with common utilities such as Makefiles, etc.
What's New in This Release: [ read full changelog ]
· This version adds STP support for Leaky integrate-and-fire neurons, fixes a Leaky integrate-and-fire neuron, and adds aspi_init_rand ().
Find us on Google+
