Revisiting Gaussian Neurons for Online Clustering with Unknown Number of Clusters
This work addresses the problem of online clustering without a fixed cluster count for applications in pattern recognition, though it appears incremental as it builds on existing Gaussian neuron methods.
The paper tackles online clustering with an unknown number of clusters by introducing a local learning rule that uses mutual repulsion of Gaussian neurons to achieve activation sparsity, and it demonstrates stable parameter learning on MNIST and CIFAR-10 datasets.
Despite the recent success of artificial neural networks, more biologically plausible learning methods may be needed to resolve the weaknesses of backpropagation trained models such as catastrophic forgetting and adversarial attacks. Although these weaknesses are not specifically addressed, a novel local learning rule is presented that performs online clustering with an upper limit on the number of clusters to be found rather than a fixed cluster count. Instead of using orthogonal weight or output activation constraints, activation sparsity is achieved by mutual repulsion of lateral Gaussian neurons ensuring that multiple neuron centers cannot occupy the same location in the input domain. An update method is also presented for adjusting the widths of the Gaussian neurons in cases where the data samples can be represented by means and variances. The algorithms were applied on the MNIST and CIFAR-10 datasets to create filters capturing the input patterns of pixel patches of various sizes. The experimental results demonstrate stability in the learned parameters across a large number of training samples.