Hierarchical Clustering using Brain-like Recurrent Attractor Neural Networks

Abstract: Hierarchical clustering is a family of machine learning methods that has many applications, amongst other data science and data mining. This thesis belongs to the research area of brain-like computing and introduces a novel approach to hierarchical clustering using a brain-like recurrent neural network. Attractor networks can cluster samples by converging to the same network state. We modulate the network behaviour by varying a parameter in the activity propagation rule such that the granularity of the resulting clustering is changed. A hierarchical clustering is then created by combining multiple levels of granularity. The method is developed for two different datasets and evaluated on a variety of clustering metrics. Its performance is compared to standard clustering algorithms and the structure and composition of the clustering is inspected. We show that the method can produce clusterings for different levels of granularity and new data without retraining. As a novel clustering method, it is relevant to machine learning applications. As a model for hierarchical recall in a memory model, it is relevant to computational neuroscience and neuromorphic computing.