An Efficient Method for online Detection of Polychronous Patterns in Spiking Neural Network
This work addresses the problem of real-time pattern recognition in neuromorphic computing, offering an incremental improvement over prior detection techniques.
The paper tackled the inefficient offline detection of polychronous patterns in spiking neural networks by introducing a new model that uses randomized codes and hash tables for online detection, demonstrating computational efficiency far exceeding existing methods on a direction-selective visual task.
Polychronous neural groups are effective structures for the recognition of precise spike-timing patterns but the detection method is an inefficient multi-stage brute force process that works off-line on pre-recorded simulation data. This work presents a new model of polychronous patterns that can capture precise sequences of spikes directly in the neural simulation. In this scheme, each neuron is assigned a randomized code that is used to tag the post-synaptic neurons whenever a spike is transmitted. This creates a polychronous code that preserves the order of pre-synaptic activity and can be registered in a hash table when the post-synaptic neuron spikes. A polychronous code is a sub-component of a polychronous group that will occur, along with others, when the group is active. We demonstrate the representational and pattern recognition ability of polychronous codes on a direction selective visual task involving moving bars that is typical of a computation performed by simple cells in the cortex. The computational efficiency of the proposed algorithm far exceeds existing polychronous group detection methods and is well suited for online detection.