TY  - GEN
ID  - cogprints3342
UR  - http://cogprints.org/3342/
A1  - Zhang, Yilu
A1  - Weng, Juyang
Y1  - 2003///
N2  - Human developmental learning is capable of
dealing with the dynamic visual world, speech-based
dialogue, and their complex real-time association.
However, the architecture that realizes
this for robotic cognitive development has
not been reported in the past. This paper takes
up this challenge. The proposed architecture does
not require a strict coupling between visual and
auditory stimuli. Two major operations contribute
to the ?abstraction? process: multiscale temporal
priming and high-dimensional numeric abstraction
through internal responses with reduced variance.
As a basic principle of developmental learning,
the programmer does not know the nature
of the world events at the time of programming
and, thus, hand-designed task-specific representation
is not possible. We successfully tested the
architecture on the SAIL robot under an unprecedented
challenging multimodal interaction mode:
use real-time speech dialogue as a teaching source
for simultaneous and incremental visual learning
and language acquisition, while the robot is viewing
a dynamic world that contains a rotating object
to which the dialogue is referring.
PB  - Lund University Cognitive Studies
KW  - autonomous mental development
KW  -  incremental hierarchial discriminant regression
KW  -  language acquisition
KW  -  SAIL
TI  - Conjunctive Visual and Auditory Development via Real-Time Dialogue
SP  - 147
AV  - public
EP  - 154
ER  -

<script src="//archive-bar.soton.ac.uk/archive-bar.js"></script>