Computationally Recognizing Causality
in an Imprecise World
Professor Lawrence J. Mazlack
Applied Artificial Intelligence Laboratory
University of Cincinnati
Causal reasoning perceptions play an essential role
in human decision-making. Recognizing and developing
causal relationships is essential for reasoning; it
forms the basis for acting intelligentially in the
world. Causal knowledge provides a deep understanding of
a system; and, the potential control over a system that
comes from being able to predict action's consequences.
Relationships with a known cause/effect relationship
have a high decision value. Causality description must
necessarily be imperfect as knowledge is imperfect and
limited. Commonsense understanding of the world tells us
that we have to deal with imprecision, uncertainty and
imperfect knowledge. Consequently, knowledge of at least
some causal effects is inherently imprecise. A
difficulty is striking a good balance between precise
formalism and commonsense imprecise reality.
Causality is imprecisely granular in many ways. Causal
complexes are groupings of smaller causal relations that
make up a large grained causal object. Usually,
commonsense reasoning is more successful in reasoning
about a few large-grained events than many fine-grained
events. However, the larger-grained causal objects are
necessarily more imprecise as some of their constituent
components. A satisficing solution might be to develop
large-grained solutions and then only go to the
finer-grain when the impreciseness of the large-grain is
Brief Biography of the Speaker:
Professor Mazlack studied computer science and applied
mathematics at Washington University (St. Louis) and
electrical engineering at both SDSM&T and Marquette
University. He received his Doctorate of Science from
Washington University. He also studied philosophy at
both Washington University and at Marquette University.
Along the way to his degrees, he did research in
computer science, electrical engineering, and biomedical
engineering. At Marquette both a Bacon Scholarship and
an athletic scholarship (football) supported him. He is
a member of the Omega Rho honorary. He has been a
visiting scholar at the University of California,
Berkeley (imprecise reasoning) and at the University of
Geneva (computational linguistics). He is on the
editorial board of several journals and has served on
the program committee of many conferences.
Dr. Mazlack currently is at the University of Cincinnati
where he is the head of the Applied Artificial
Intelligence Laboratory and the chair of the Data and
Knowledge Management research group. Beyond academia, at
a large computer company, he was responsible for
database software development. He has been closely
involved with several small company startups. Away from
technology, he has been professionally active in the
visual, written, and dramatic arts.
Dr. Mazlack's current research is directed toward three
• Causality, both theoretical and applied to
• Unsupervised data mining and the closely associated
topic of autonomous recognition of web page ontologies
in the context of the Semantic Web.
• Clustering multi-modal computational objects.
These interests are in the context of broader interests
in: soft computing, natural language understanding,
artificial intelligence, and databases.