Next: The Overall Architecture
Previous: Playpen's Task
Playpen's architecture and behavior are
constrained both by the nature of its task and what is
known about how language and vision operate.
- As discussed in Sections 3.2.1
above, processing is interactive and
bi-directional. Visual input can yield linguistic output, and
linguistic input, along with some visual context, can yield visual
output in the form of expectations or imagery.
- In the pre-linguistic phase, the
system receives visual inputs
with no explicit labels, and learning consists of somehow extracting
regularity from these inputs.
In the linguistic phase, some visual inputs are accompanied by
linguistic inputs as well.
In one sense this just means that the input patterns are more complex;
in another it means that there are now new independent grounds for
dividing space up into particular categories.
- Language is explicit about certain categories, in particular
objects and relations.
Learning language requires that the network have the capacity to
represent these categories explicitly.
- A good deal is known about the human vision system.
While we believe there are large gaps that need to be filled in, the
model should be in general agreement with the vision facts.
- A good deal is known about
language development and
Playpen is meant to model the behavior of babies, and
the most important constraints are those concerned with development:
What precedes what? What is hard or easy?
We have paid most attention to the first four constraints.
The fifth is likely to play a greater role as we model the
development of particular relations.
Mon Jun 23 04:27:19 EST 1997