Biologically inspired computation and learning in sensorimotor systems

Daniel D. Lee, H. Sebastian Seung

Research output: Contribution to journalConference articlepeer-review

1 Scopus citations


Networking systems presently lack the ability to intelligently process the rich multimedia content of the data traffic they carry. Endowing artificial systems with the ability to adapt to changing conditions requires algorithms that can rapidly learn from examples. We demonstrate the application of such learning algorithms on an inexpensive quadruped robot constructed to perform simple sensorimotor tasks. The robot learns to track a particular object by discovering the salient visual and auditory cues unique to that object. The system uses a convolutional neural network that automatically combines color, luminance, motion, and auditory information. The weights of the networks are adjusted using feedback from a teacher to reflect the reliability of the various input channels in the surrounding environment. Additionally, the robot is able to compensate for its own motion by adapting the parameters of a vestibular ocular reflex system.

Original languageEnglish (US)
Pages (from-to)4-11
Number of pages8
JournalProceedings of SPIE - The International Society for Optical Engineering
StatePublished - 2001
Externally publishedYes
EventApplications and Science of Neural Networks, Fuzzy Systems, and Evolutionary Computation IV - San Diego, CA, United States
Duration: Jul 31 2001Aug 2 2001

All Science Journal Classification (ASJC) codes

  • Electronic, Optical and Magnetic Materials
  • Condensed Matter Physics
  • Applied Mathematics
  • Electrical and Electronic Engineering
  • Computer Science Applications


  • Computational Neuroscience
  • Neural Networks


Dive into the research topics of 'Biologically inspired computation and learning in sensorimotor systems'. Together they form a unique fingerprint.

Cite this