Three Challenges for Machine Learning Research
Thomas G. Dietterich
School of Electrical Engineering and Computer Science
Oregon State University,
Abstract:
Over the past 25 years, machine learning research
has made huge progress on the problem of supervised learning.
This talk will argue that now is the time to consider three new
directions.
The first direction, which is already being pursued by many groups,
is Structural Supervised Learning in which the input instances
are no longer independent and identically distributed but instead
are related by some kind of sequential, spatial, or graphical
structure. A variety of methods are being developed, including
hidden Markov support vector machines, conditional random fields,
and sliding window techniques.
The second new direction is Transfer Learning in
which something is learned on one task that can help with a second,
separate task. This includes transfer of learned facts, learned
features, and learned ontologies. How can we measure transfer
learning? How can be achieve it?
The third new direction is Deployable Learning
Systems. Today's learning systems are primarily operated offline
by machine learning experts. They provide an excellent way of
constructing certain kinds of AI systems (e.g., speech recognizers,
handwriting recognizers, data mining systems, etc.). But it is
rare to see learning systems that can be deployed in real applications
in which learning takes place on-line and without expert intervention.
Deployed learning systems must deal with such problems as changes
in the number, quality, and semantics of input features, changes
in the output classes, and changes in the underlying probability
distribution of instances.
There are also difficult software engineering issues
that must be addressed in order to make learning systems maintainable
after they are deployed.
[ ]
|