Unsupervised Learning with Self-Organizing Spiking Neural Networks
This work addresses unsupervised learning in spiking neural networks, offering incremental advancements in biologically-inspired classification methods.
The paper tackles unsupervised learning by hybridizing self-organized maps with spiking neural networks, developing inhibition strategies and classification tools, resulting in improvements over state-of-the-art spiking neural networks.
We present a system comprising a hybridization of self-organized map (SOM) properties with spiking neural networks (SNNs) that retain many of the features of SOMs. Networks are trained in an unsupervised manner to learn a self-organized lattice of filters via excitatory-inhibitory interactions among populations of neurons. We develop and test various inhibition strategies, such as growing with inter-neuron distance and two distinct levels of inhibition. The quality of the unsupervised learning algorithm is evaluated using examples with known labels. Several biologically-inspired classification tools are proposed and compared, including population-level confidence rating, and n-grams using spike motif algorithm. Using the optimal choice of parameters, our approach produces improvements over state-of-art spiking neural networks.