              |
Daniel D. LeeAssociate Professor, ESE Research InterestsMachine Learning Algorithms: Why
is it that if computers have gotten so much faster and cheaper,
they have not become any better at understanding what we want them
to do? Some of the tasks we take for granted such as vision and
language are still too difficult for the fastest supercomputers
to handle. To us, a picture may be worth a thousand words, but to
a machine it's just a seemingly random jumble of numbers. How can
we get machines to intelligently process this kind of information? Current ProjectsRepresentative PublicationsA
kernel view of the dimensionality reduction of manifolds Nonnegative
deconvolution for time of arrival estimation
Short-term memory in orthogonal neural networks
Spontaneous eye movements in goldfish: oculomotor integrator performance,
plasticity, and dependence on visual feedback Learning
high dimensional correspondences with low dimensional manifolds
Equilibrium properties of temporally asymmetric Hebbian plasticity Stability
of the memory of eye position in a recurrent network of conductance-based
model neurons The
manifold ways of perception Learning
the parts of objects with nonnegative matrix factorization Teaching
|
|
Contact Information
|
