Construction of a “Neuron Activity–Class” Mapping in a Convolutional Spiking Neural Network with STDP Training

This paper investigates the problem of constructing a mapping between the spiking activity of a convolutional spiking neural network and the class of an input image. This problem arises after unsupervised training: the convolutional layer forms an event-based representation of the image, but the network itself does not contain a ready-made mechanism for assigning a class label. The aim of the study is to evaluate how informative the spike counters of the convolutional layer are after training with the STDP rule (Spike-Timing-Dependent Plasticity, a biologically plausible learning rule for impulse-based, or spiking, neural networks) and to assess the performance of a linear readout classifier as the number of training presentations increases. The experiments were conducted on the MNIST dataset, a standard dataset of handwritten digit images. A single-layer architecture was used: one convolutional layer with 32 feature maps, a 5 × 5 kernel, and an output dimensionality of 32 × 24 × 24, corresponding to 18432 LIF neurons, where LIF denotes the leaky integrate-and-fire neuron model. The input images were encoded using a deterministic Poisson encoder; the Poisson encoding multiplier was set to 0.006. The presentation duration, that is, the time during which an object was shown to the network, was 100 time steps. Training was performed from scratch using the STDP rule, without resuming from a previously saved state. For evaluation, a protocol was used in which spike counters were collected on 10000 training images and 10000 test images. In the main experiment, with 15 000 STDP training presentations, an accuracy of 0.8883 was achieved. The baseline label-map approach, close to the method of Diehl and Cook, produced an accuracy of about 0.48 under the same configuration. The coverage of the calibrated label map was 219 out of 18 432 neurons, while the average activity was 4146.9416 spikes per image. The neighboring scale point with 10 000 training presentations yielded an accuracy of 0.8876. The results show that the chosen method for reading out activity has a substantial effect on the final classification quality: a linear readout classifier based on the full vector of network spike counters extracts distributed information that is lost when labels are assigned directly to individual neurons.