ANNarchy (Artificial Neural Networks architect)
ANNarchy is a simulator for distributed mean-rate or spiking neural networks. The core of the library is written in C++ and provides an interface in Python. The current development version is 3.0 and will be soon released under the GNU GPL.ANNarchy is made to simulate distributed and biologically plausible neural networks, which means that neurons have only access to local information through their connections to other neurons but not to global information, like the state of the entire network or connections of other neurons. In principle, biologically unplausible mechanisms like back-propagation and winner-take-all are not well-suited for this simulator.
Architecture
ANNarchy is specifically oriented towards the learning capabilities of the neural networks. The main object, annarNetwork, is a collection of interconnected heterogeneous populations of artificial neurons (annarPopulation). Each population comprises a set of similar artificial neurons, annarNeuron, whose activation is ruled by various differential equations. This activation of a neuron depends on the one of other neurons of the networks from which it receives connections (through synapses, annarWeight).The connections received by a neuron are stored in different arrays, depending on the type that was assigned to them: realistic neurons do not integrate equally all their inputs, but differentially process them depending on their neurotransmitter type (AMPA, NMDA, GABA, dopamine...), position on the dendritic tree (proximal/distal) or even region of origin (cortical columns do not treat thalamic inputs the same way as long-distance cortico-cortical connections). Each type of connection can be integrated separately to modify the activation of a neuron.
This typed organization of afferent connections also allows to easily apply to them different learning rules (Hebbian, Anti-Hebbian, dopamine-modulated, STDP...) A learning rule is defined in the annarLearningRule class and can be reused in different networks.
A class representing the external world, annarWorld, allows the network to interact with its environment in an input/output manner (retrieving input images, performing actions...)
Implementation
The core of the computations is performed in C++ and distributed over all available cores thanks to openMP. Users can inherit from the provided classes in order to implement their own activation functions and learning rules.An interface to Python is provided thanks to Boost.Python
A portage of ANNarchy to the CUDA framework is currently under development.
Releases
To obtain a beta version of the current ANNarchy 3.0 source code, please send an email to julien dot vitay at informatik dot tu-chemnitz dot de.History of versions:
- 1.0: Initial version, purely C++.
- 1.1: Management of exceptions.
- 1.3: Parallelization of the computation using openMP.
- 2.0: Optimized version with separated arrays for typed connections.
- 2.1: Parallelization using CUDA (in development).
- 3.0: Python interface.
