skip to main content
Resource type Show Results with: Show Results with: Index

A Neural Network for Semi-Supervised Learning on Manifolds

Genkin, Alexander ; Sengupta, Anirvan M. ; Chklovskii, Dmitri

Artificial Neural Networks and Machine Learning - ICANN 2019 (pp. 375-386). Springer International Publishing [Peer Reviewed Journal]

Link to full text

Citations Cited by
  • Title:
    A Neural Network for Semi-Supervised Learning on Manifolds
  • Author/Creator: Genkin, Alexander ; Sengupta, Anirvan M. ; Chklovskii, Dmitri
  • Subjects: Computer Science - Machine Learning ; Statistics - Machine Learning
  • Is Part Of: Artificial Neural Networks and Machine Learning - ICANN 2019 (pp. 375-386). Springer International Publishing
  • Description: Semi-supervised learning algorithms typically construct a weighted graph of data points to represent a manifold. However, an explicit graph representation is problematic for neural networks operating in the online setting. Here, we propose a feed-forward neural network capable of semi-supervised learning on manifolds without using an explicit graph representation. Our algorithm uses channels that represent localities on the manifold such that correlations between channels represent manifold structure. The proposed neural network has two layers. The first layer learns to build a representation of low-dimensional manifolds in the input data as proposed recently in [8]. The second learns to classify data using both occasional supervision and similarity of the manifold representation of the data. The channel carrying label information for the second layer is assumed to be "silent" most of the time. Learning in both layers is Hebbian, making our network design biologically plausible. We experimentally demonstrate the effect of semi-supervised learning on non-trivial manifolds. Comment: 12 pages, 4 figures, accepted in ICANN 2019
  • Identifier: Arxiv ID: 1908.08145