Linear readout of object manifolds

Sueyeon Chung, Daniel D. Lee, Haim Sompolinsky*

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

20 Scopus citations

Abstract

Objects are represented in sensory systems by continuous manifolds due to sensitivity of neuronal responses to changes in physical features such as location, orientation, and intensity. What makes certain sensory representations better suited for invariant decoding of objects by downstream networks? We present a theory that characterizes the ability of a linear readout network, the perceptron, to classify objects from variable neural responses. We show how the readout perceptron capacity depends on the dimensionality, size, and shape of the object manifolds in its input neural representation.

Original languageEnglish
Article number060301
JournalPhysical Review E
Volume93
Issue number6
DOIs
StatePublished - 30 Jun 2016

Bibliographical note

Publisher Copyright:
© 2016 American Physical Society.

Fingerprint

Dive into the research topics of 'Linear readout of object manifolds'. Together they form a unique fingerprint.

Cite this