Hyperseed: Unsupervised Learning with Vector Symbolic Architectures
This work addresses the need for efficient unsupervised learning algorithms suitable for neuromorphic hardware, though it appears incremental in applying VSA principles to existing methods.
The paper tackles the problem of unsupervised learning for fast topology-preserving feature maps using Vector Symbolic Architectures, achieving few-shot learning and a single-vector operation rule, with empirical validation on synthetic datasets, IRIS classification, and language identification tasks.
Motivated by recent innovations in biologically-inspired neuromorphic hardware, this article presents a novel unsupervised machine learning algorithm named Hyperseed that draws on the principles of Vector Symbolic Architectures (VSA) for fast learning of a topology preserving feature map of unlabelled data. It relies on two major operations of VSA, binding and bundling. The algorithmic part of Hyperseed is expressed within Fourier Holographic Reduced Representations model, which is specifically suited for implementation on spiking neuromorphic hardware. The two primary contributions of the Hyperseed algorithm are, few-shot learning and a learning rule based on single vector operation. These properties are empirically evaluated on synthetic datasets as well as on illustrative benchmark use-cases, IRIS classification, and a language identification task using n-gram statistics. The results of these experiments confirm the capabilities of Hyperseed and its applications in neuromorphic hardware.