NEDIS-NNLGApr 10, 2017

Unsupervised prototype learning in an associative-memory network

arXiv:1704.02848v21 citations
Originality Incremental advance
AI Analysis

This work addresses unsupervised representation learning for AI systems, offering a method to abstract data into prototypes, but it appears incremental as it builds on existing Hopfield and Boltzmann machine frameworks.

The paper tackled unsupervised learning in a generalized Hopfield associative-memory network by proving its equivalence to a semi-restricted Boltzmann machine and demonstrating that it learns prototypes as internal representations of input data, with a spectral method proposed to extract concise idealized prototypes.

Unsupervised learning in a generalized Hopfield associative-memory network is investigated in this work. First, we prove that the (generalized) Hopfield model is equivalent to a semi-restricted Boltzmann machine with a layer of visible neurons and another layer of hidden binary neurons, so it could serve as the building block for a multilayered deep-learning system. We then demonstrate that the Hopfield network can learn to form a faithful internal representation of the observed samples, with the learned memory patterns being prototypes of the input data. Furthermore, we propose a spectral method to extract a small set of concepts (idealized prototypes) as the most concise summary or abstraction of the empirical data.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes