| |
Abstract:
Spatial information comes in two forms: direct spatial
information (for example, retinal position) and indirect temporal
contiguity information, since objects encountered sequentially are
spatially close. The acquisition of spatial information by a neural
network is investigated here. Given a spatial layout of several
objects, networks are trained on a prediction task. Networks using
temporal sequences with no direct spatial information are found to
develop internal representations that show distances correlated
with distances in the external layout. The influence of spatial
information is analyzed by providing direct spatial information to
the system during training that is either consistent with the
layout or inconsistent with it. This approach allows examination of
the relative contributions of spatial and temporal
contiguity.
|
