Unsupervised Learning with Self-Organizing Spiking Neural Networks

Abstract

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.

Lattice map spiking neural networks (LM-SNNs) for clustering and classifying image data

“…This section summarizes the applied spiking neural network structure and learning algorithms using leaky integrate-and-fire (LIF) neurons and spike-timing-dependent plasticity (STDP), as initially outlined in [14], extended in [25,32], and supplemented in [33] with inter-neuron distance-dependent inhibition strength.…”

“…We demonstrate increased learning speed on machine learning tasks due to these architectural change. Next, we describe the PyTorch-based BindsNET 1 simulator [32,33], where we were able to replicate previous results using the BRIAN library and implement new experiments based on the greater flexibility of BindsNET. The employed testbeds include images from MNIST dataset [34] and images obtained by the Atari Breakout game.…”

“…Here we summarize results obtained with the LM-SNN models using MNIST data; for additional details, see [25,33]. We omit results on the increasing and growing inhibition strategies in favor of results using the simpler two-level inhibition strategy.…”

“…Table 3 The smaller networks were trained for a single pass, while we conducted a 3-pass training for the 1,225 and 1,600 networks to explore peak accuracies. Detailed results with all single passes are given in [33]. To further evaluate the classification ability that is proposed in this paper, we compute average confusion matrices ( Figure 5) for networks with 1,600 neurons from Table 3, for the best classification scheme (n − gram; 94.07%), the second-best (distance; 93.03%), and the worst (baseline Diehl & Cook; 92.80%).…”

A Bin Encoding Training of a Spiking Neural Network Based Voice Activity Detection

“…Some algorithms are based on supervised learning techniques, such as the nonrecurrent SNN developed in [6] that extracts the spike features from speech signals, and the framework for sound recognition presented in [7]. Unsupervised learning is exploited in other approaches for both feature extraction [8] and isolated word classification utilizing the principles of Self-Organizing Maps [9,10]. Some studies use instead a reservoir based-technique to solve the task of isolated digit recognition [11,12].…”