Sensitivity of Sparse Codes to Image Distortions

Kyle Luther, H. Sebastian Seung

Research output: Contribution to journalArticlepeer-review


Sparse coding has been proposed as a theory of visual cortex and as an unsupervised algorithm for learning representations. We show empirically with the MNIST data set that sparse codes can be very sensitive to image distortions, a behavior that may hinder invariant object recognition. A locally linear analysis suggests that the sensitivity is due to the existence of linear combinations of active dictionary elements with high cancellation. A nearest-neighbor classifier is shown to perform worse on sparse codes than original images. For a linear classifier with a sufficiently large number of labeled examples, sparse codes are shown to yield higher accuracy than original images, but no higher than a representation computed by a random feedforward net. Sensitivity to distortions seems to be a basic property of sparse codes, and one should be aware of this property when applying sparse codes to invariant object recognition.

Original languageEnglish (US)
Pages (from-to)1616-1635
Number of pages20
JournalNeural computation
Issue number7
StatePublished - Jun 16 2022

All Science Journal Classification (ASJC) codes

  • Arts and Humanities (miscellaneous)
  • Cognitive Neuroscience


Dive into the research topics of 'Sensitivity of Sparse Codes to Image Distortions'. Together they form a unique fingerprint.

Cite this