[Back]


Talks and Poster Presentations (with Proceedings-Entry):

K. Selyunin, D. Ratasich, E. Bartocci, A. Islam, S. Smolka, R. Grosu:
"Neural Programming: Towards Adaptive Control in Cyber-Physical Systems";
Talk: 54th IEEE Conference on Decision and Control, Osaka, Japan; 2015-12-15 - 2015-12-18; in: "Proc. of CDC 2015: the 54th IEEE Conference on Decision and Control", IEEE Computer Society, (2015), ISBN: 978-1-4799-7884-7; 6978 - 6985.



English abstract:
We introduce \emph{Neural Programming} (NP), a novel paradigm for
writing adaptive controllers for Cyber-Physical Systems (CPSs).
In NP, {\em if} and {\em while} statements, whose discontinuity is
responsible for frailness in CPS design and implementation, are
replaced with their smooth (probabilistic) neural {\em nif} and
{\em nwhile} counterparts. This allows one to write robust and
adaptive CPS controllers as dynamic neural networks (DNN).
Moreover, with NP, one can relate the thresholds occurring in
soft decisions with a Gaussian Bayesian network (GBN). We provide
a technique for learning these GBNs using available domain
knowledge. We demonstrate the utility of NP on three case
studies: an adaptive controller for the parallel parking of a
Pioneer rover; the neural circuit for tap withdrawal in
\emph{C.\ elegans}; and a neural-circuit encoding of parallel
parking which corresponds to a proportional
controller. To the best of our knowledge, NP is the first
programming paradigm linking neural networks (artificial or
biological) to programs in a way that explicitly highlights
a program's neural-network structure.


"Official" electronic version of the publication (accessed through its Digital Object Identifier - DOI)
http://dx.doi.org/10.1109/CDC.2015.7403319