Learning by coincidence: Siamese networks and common variable learning

Uri Shaham, Roy R. Lederman

Research output: Contribution to journalArticlepeer-review

24 Scopus citations


We consider the statistical problem of learning a common source of variability in data which are synchronously captured by multiple sensors, and demonstrate that Siamese neural networks can be naturally applied to this problem. This approach is useful in particular in exploratory, data-driven applications, where neither a model nor label information is available. In recent years, many researchers have successfully applied Siamese neural networks to obtain an embedding of data which corresponds to a “semantic similarity”. We present an interpretation of this “semantic similarity” as learning of equivalence classes. We demonstrate the ability of Siamese networks to learn common variability in a range of experiments on synthetic and real-world data, and demonstrate the potential of Siamese networks to provide new leads for data-driven research through unsupervised learning in cancer data.

Original languageEnglish
Pages (from-to)52-63
Number of pages12
JournalPattern Recognition
StatePublished - 1 Feb 2018
Externally publishedYes


  • Common variable
  • Representation learning
  • Siamese networks
  • Similarity learning
  • Unsupervised learning

ASJC Scopus subject areas

  • Software
  • Signal Processing
  • Computer Vision and Pattern Recognition
  • Artificial Intelligence


Dive into the research topics of 'Learning by coincidence: Siamese networks and common variable learning'. Together they form a unique fingerprint.

Cite this