For neural networks, function determines form

Francesca Albertini, Eduardo D. Sontag

Research output: Contribution to journalArticlepeer-review

36 Scopus citations


This article shows that the weights of continuous-time feedback neural networks are uniquely identifiable from input/output measurements. Under weak genericky assumptions, the following is true: Assume given two nets, whose neurons all have the same nonlinear activation function a; if the two nets have equal behaviors as “black boxes” then necessarily they must have the same number of neurons and—except at most for sign reversals at each node—the same weights. Moreover, even if the activations are not a priori known to coincide, they are shown to be also essentially determined from the external measurements.

Original languageEnglish (US)
Pages (from-to)975-990
Number of pages16
JournalNeural Networks
Issue number7
StatePublished - 1993

All Science Journal Classification (ASJC) codes

  • Cognitive Neuroscience
  • Artificial Intelligence


  • Control systems
  • Identification from input/output data
  • Neural networks


Dive into the research topics of 'For neural networks, function determines form'. Together they form a unique fingerprint.

Cite this