Title: Sensorimotor Learning and the Development of Position Invariance
1Sensorimotor Learning and the Development of
Position Invariance Muhua Li and James J. Clark
- Biological the position invariance property of
many higher-level visual cortex neurons. - Theoretical the sensorimotor contingency theory
of ORegan and Noe 1 which holds that
perception is based on the laws relating motor
activity and the resulting sensory input.
Motivation
Learning Procedure
Simulation Results
Our techniques are applied to the invariant
representation of images of straight lines. The
projection of straight lines in space onto the
spherical retinal surface will form 2D curvatures
that vary with eccentricity.
- In cases with a 10 undershooting probability in
the training data - Without feedback, the estimated canonical
images associate the undershot stimuli as well as
the foveal stimuli with the input peripheral
feature stimuli. - With feedback, the network is able to discard
the disturbance from the undershot stimuli and
make the correct association.
Enhanced Algorithm
A feedback from the higher-level layer is used to
handle cases where the saccade does not succeed
in foveating the target, but instead undershoots
the target, at which point a small corrective
saccade is made.
Basic Learning Rules
References 1 ORegan, J.K. and Noe, A. A
sensorimotor account of vision and visual
consciousness, submitted to Behavioral and Brain
Sciences. 2 Clark, J.J. Sensorimotor
development of position invarianct feature
detectors, ICPR2002
V is the association matrix relating pre- and
post-saccadic stimuli. is the foveal stimuli
(post-motor) as the reinforcement reward. The
pre-motor stimulus X is held in a short-term
memory generating an eligibility trace , which
will be used to enhance, in a Hebbian fashion,
the association to the post-motor stimulus.
The reinforcement reward is composed of both the
post-saccade stimulus and its estimated canonical
image, which are weighted by a confidence