|
The field of
Artificial Intelligence (AI) is concerned both with modeling human
intelligence and with solving complex problems not solvable by
simple or analytic procedures. For instance, a major, long-range
goal of AI is the construction of an intelligent robot, one capable
of perceiving, acting, comprehending, reasoning, and learning in
complex environments. The AI field at UCLA consists of six related
areas:
- Problem solving
& search -- A fundamental technique in AI is to encode a
problem as a state space in which solutions are goal states in that
space. Thus, problem solving can be viewed as state space search.
To search large, combinatorial state spaces, knowledge (e.g.
heuristics) and planning are required.
- Knowledge
Representation -- Intelligent behavior often requires
knowledge. For example, language comprehension requires encoding
the meanings of words and how they are combined. Techniques for
representing knowledge include use of semantic networks, logic
programming, and neural networks.
- Natural
Language Processing (NLP) -- Language is the major medium for
communicating thought and knowledge. NLP is concerned with mappings
between language and thought, how language skills are learned, and
how knowledge is acquired through language (e.g.
reading).
- Reasoning
Systems -- Most human reasoning occurs in task/domains with
uncertain, ill-defined and incomplete knowledge. Reasoning in such
domains requires techniques such as use of default, probabilistic,
and non-monotonic logics.
- Vision &
Perception -- Images are fraught with ambiguity, e.g., wiggly
lines could represent ocean waves, a person's hair, snakes, etc.
Low-level vision is concerned with extracting visual features from
color, texture, edges, and so forth, while high-level vision deals
with how to represent and form internal models of complex shapes
and structured objects.
- Neural Networks
(NNs) -- These parallel, distributed processing networks excel
in automatic category formation, classification and associative
recall. They tend to be fault/noise tolerant and exhibit graceful
degradation when "lesioned". One area of research in AI is how to
integrate NN and symbolic AI techniques to solve outstanding
problems in NLP, reasoning, perception and problem
solving.
|