Synthesis of neural networks for spatio-temporal spike pattern recognition and processing
This addresses the need for efficient neural synthesis algorithms in large-scale computational platforms, offering a domain-specific improvement over existing methods like the Neural Engineering Framework.
The authors tackled the problem of synthesizing neural networks for cognitive tasks by developing a method that generates sparse synaptic connectivity for time-encoded spike signals, enabling arbitrary specification of neuronal characteristics and fast optimization, and demonstrated it by recognizing sparsely encoded speech with improved efficiency.
The advent of large scale neural computational platforms has highlighted the lack of algorithms for synthesis of neural structures to perform predefined cognitive tasks. The Neural Engineering Framework offers one such synthesis, but it is most effective for a spike rate representation of neural information, and it requires a large number of neurons to implement simple functions. We describe a neural network synthesis method that generates synaptic connectivity for neurons which process time-encoded neural signals, and which makes very sparse use of neurons. The method allows the user to specify, arbitrarily, neuronal characteristics such as axonal and dendritic delays, and synaptic transfer functions, and then solves for the optimal input-output relationship using computed dendritic weights. The method may be used for batch or online learning and has an extremely fast optimization process. We demonstrate its use in generating a network to recognize speech which is sparsely encoded as spike times.