|
Showing 1 - 3 of
3 matches in All Departments
One high-level ability of the human brain is to understand what it
has learned. This seems to be the crucial advantage in comparison
to the brain activity of other primates. At present we are
technologically almost ready to artificially reproduce human brain
tissue, but we still do not fully understand the information
processing and the related biological mechanisms underlying this
ability. Thus an electronic clone of the human brain is still far
from being realizable. At the same time, around twenty years after
the revival of the connectionist paradigm, we are not yet satisfied
with the typical subsymbolic attitude of devices like neural
networks: we can make them learn to solve even difficult problems,
but without a clear explanation of why a solution works. Indeed, to
widely use these devices in a reliable and non elementary way we
need formal and understandable expressions of the learnt functions.
of being tested, manipulated and composed with These must be
susceptible other similar expressions to build more structured
functions as a solution of complex problems via the usual deductive
methods of the Artificial Intelligence. Many effort have been
steered in this directions in the last years, constructing
artificial hybrid systems where a cooperation between the sub
symbolic processing of the neural networks merges in various modes
with symbolic algorithms. In parallel, neurobiology research keeps
on supplying more and more detailed explanations of the low-level
phenomena responsible for mental processes.
One high-level ability of the human brain is to understand what it
has learned. This seems to be the crucial advantage in comparison
to the brain activity of other primates. At present we are
technologically almost ready to artificially reproduce human brain
tissue, but we still do not fully understand the information
processing and the related biological mechanisms underlying this
ability. Thus an electronic clone of the human brain is still far
from being realizable. At the same time, around twenty years after
the revival of the connectionist paradigm, we are not yet satisfied
with the typical subsymbolic attitude of devices like neural
networks: we can make them learn to solve even difficult problems,
but without a clear explanation of why a solution works. Indeed, to
widely use these devices in a reliable and non elementary way we
need formal and understandable expressions of the learnt functions.
of being tested, manipulated and composed with These must be
susceptible other similar expressions to build more structured
functions as a solution of complex problems via the usual deductive
methods of the Artificial Intelligence. Many effort have been
steered in this directions in the last years, constructing
artificial hybrid systems where a cooperation between the sub
symbolic processing of the neural networks merges in various modes
with symbolic algorithms. In parallel, neurobiology research keeps
on supplying more and more detailed explanations of the low-level
phenomena responsible for mental processes.
The potential of parallelism in logic reaches far beyond the
exploitation of AND- and OR-parallelism usually found in attempts
to parallelize PROLOG. This book discusses parallelism in logic and
its exploitation on parallel architectures. A variety of categories
of parallelism is discussed with respect to different levels of a
logical formula and different ways to evaluate it. As an outcome of
these investigations it is shown that modularity allows s
tructuring of logic programs and meta-evaluation can be used to c
ontrol the evaluation process on a parallel system. This combinat
ion yields a consistent programming framework with a wide scope.
Finally, the suitability of a specific evaluation mechanism for p
arallel architectures is investigated.
|
|