Todd K. Leen, Professor
Research Interests -
My research in machine learning focused along several threads including
theory and algorithm synthesis,
with
applications to health care, signal processing, fault
detection, and modeling in complex systems. I also have
collaborative projects in computational neuroscience.
Health Care Applications of Machine Learning
I collaborate with Misha
Pavel, Tamara Hayes,
and
Deniz
Erdogmus in the OHSU Point
of Care Laboratory (POCL) and with Jeff Kaye director of OHSU's Layton Againg &
Alzheimer's Disease Center. My work with these colleagues is
aimed at detecting behavioral changes that are predictive of emerging
health problems, particularly cognitive decline. This work makes
use of a number of novel unobstrusive in-home monitoring technologies
(see POCL) to provide early
detection of health-related changes. There are early results of
our machine learning applications to this work in ICML08, ICASSP08,
and NIPS09.
Environmental Observation and Forecasting Systems
I've enjoyed a long collaboration with Antonio Baptista and OGI's Center
for Coastal and
Land-Margin Research. Our work with CCALMR's CORIE project
is aimed at improving reliability of measurements and modeling for the
Columbia River estuary. Our system
for detecting sensor degradation cut salinity data loss by over
50%. We have applied learning technology
as key elements in a
(problem-portable) data assimilation
(model / data fusion) system. Ours is the first data assimilation
system to operate successfully in a strongly non-linear
river-estuarine-ocean system. The system
makes novel use of neural networks trained to emulate the dynamics of
an
extremely large (10^7 degrees of freedom) finite element model of the
system. These emulators, or model
surrogates, provide a reduction in the time required for model
evaluation by a factor of one
to
twelve
thousand, enabling a dramatic increase in ensemble
prediction capability.
Computational Neuroscience 
Drs. Pat
Roberts, Nathan
Sawtell and myself have an NSF project on sensory-motor processing
and
memory in the mormyrid weakly
electric fish.
These fish have an electro-location system that uses the animal's
electric organ discharge (EOD) to navigate, explore objects, and find
prey. The electrosensory lateral line lobe (ELL) of the mormyrid
fish integrates motor command, proprioceptive, and electrosensory
information in a cerebellar-like structure. This structure
performs
early electrosensory processing. As part of its function, the
ELL generates memories comprising the expected sensory signal from the
fish's own electric discharge. These memories are adaptive
through spike-timing-dependent plasticity. The project integrates
modeling and neurophysiology experiments to determine how realistic
patterns of
excitation are processed in ELL, and how plasticity is controlled by
recurrent connections from higher centers. As part of the
project, we are developing a
novel computer-controlled stimulus system that provides
precise control of the spatio-temporal profile of the electric images
on the fish's skin.
Neural
Information
Processing Systems (NIPS) Conferences
I served as Program Chair in 1999 and General Chair
in 2000.
CV pdf.
Other
Fun Stuff
Surrogate Movies Plume Estuary
