UTCS Colloquium/AI: Terran Lane/University of New Mexico Scientific Data Mining: The Discovery and Use of Complex Networks in Neuroscience and Genomics ACES 2.402 Friday December 7 2007 11:00 a.m.

Contact Name: 
Jenna Whitney
Dec 7, 2007 11:00am - 12:00pm

There is a sign up schedule for this event:

Type of Talk: UTCS Colloquium/AI

Speaker/Affiliation: Terran
Lane/University of New Mexico

Date/Time: Friday December 7 2007
11:00 a.m.

Host: Ray Mooney

Talk Title: Scientific Data Min

ing: The Discovery and Use of Complex Networks in Neuroscience and Genomics

Talk Abstract:
Modern science is overwhelmed by a sea of data. R

ecent years have
brought us sensor technologies that produce gigabytes

to terabytes of
information per experiment: functional neuroimaging tech

nologies genetic
microarrays and high-throughput assays digital telesc

opes and environ-
mental sensor networks to name just a few. These tec

hnologies offer
unprecedented opportunity for scientific discovery to th

e domain scientists.
Yet at the same time they present a daunting anal

ysis task: to extract
meaningful substantiable patterns from this overw

helming mass of data.
Further the data are typically extremely noisy an

d the patterns of interest
are often multivariate and nonlinear.

To address these analysis problems computer scientists in the machine

learning and data mining communities have been developing the field of

cientific data mining: using advanced computational and statistical tools <

br>to extract complex patterns from large difficult scientific data sets.

In this talk I will give an overview of my recent work on scientif

ic data
mining in two different domains: neuroscience and genomics. On

former front I will discuss the problem of network identification:
the network of functional activity interactions that underlies
behavioral pattern. The ability to find such networks is critical
neuroscientists who are working to understand mental illnesses such

as dementia or schizophrenia. On the latter front I will discuss the

of biological parameter estimation for RNA interference (RNAi). In
case we use the structure of known activity networks to infer pa

of the biological process that produced it. These parameters

in turn help
biologists and pharmacists develop better RNAi-based genet

ic screens and

Speaker Bio:
Terran Lane is As

sistant Professor of computer science at the University
of New Mexico.

His primary academic interests are: machine learning;
reinforcement lea

rning behavior and control; and artificial intelligence in
general. H

e is also interested in computer/information security/privacy and