Access
To read this story in full you will need to login or make a payment (see right).
insight
Nature 431, 768-774 (14 October 2004) | doi:10.1038/nature03014; Published online 13 October 2004
Open Innovation Challenges
- More Challenges
- Powered by:
nature jobs
Research Fellow in Bone-ligamentous Tissue Scaffolds
- University of Leeds
- Leeds, UK
Faculty Position in Mathematical Biology
- The Ohio State University
- Ohio, USA
review article Generalization in vision and motor control
Tomaso Poggio1 & Emilio Bizzi1,2
Abstract
Learning is more than memory. It is not simply the building of a look-up table of labelled images, or a phone-directory-like list of motor acts and the corresponding sequences of muscle activation. Central to learning and intelligence is the ability to predict, that is, to generalize to new situations, beyond the memory of specific examples. The key to generalization, in turn, is the architecture of the system, more than the rules of synaptic plasticity. We propose a specific architecture for generalization for both the motor and the visual systems, and argue for a canonical microcircuit underlying visual and motor learning.
To read this story in full you will need to login or make a payment (see right).
MORE ARTICLES LIKE THIS
These links to content published by NPG are automatically generated.
NEWS AND VIEWS
Computational neuroscience Building blocks of movementNature News and Views (12 Oct 2000)
Predicting the visual world: silence is goldenNature Neuroscience News and Views (01 Jan 1999)
News On Views: Pandemonium RevisitedNature Neuroscience News and Views (01 Nov 1999)
Population vectors and motor cortex: neural coding or epiphenomenon?Nature Neuroscience News and Views (01 Apr 2000)
