Grant: Discovery Grants Program - Individual
University of Ottawa
$14,000.00
Robust learning and evaluation with impoverished training data
FY 2007-08
Summary
Being able to predict what will happen in the near future, with reasonable confidence, is an essential skill of humans and computers alike. Knowing what will come next allows people to plan ahead and use their resources efficiently and effectively. For computers to be useful tools, they must emulate this practice. Computers must plan ahead, predicting a user's needs and finding any items that may satisfy them.As with humans, computers can learn from past experience. But most research so far has assumed that the experience directly carries to the new problem. In recent times this assumption has become under increasing scrutiny. This project explores the impact of removing this assumption.If the change from past experience to a new problem is too large prior experience will not be useful. So some idea of the range and type of changes that a learning system will experience has be obtained. How well existing systems cope with these changes needs analyzing. This will lead to new variants of such algorithms or totally new algorithms that are robust to these changes.This proposal requests funds solely to support graduate students. It represents a good research topic for new researchers. Those trained in this area will have strong potential as researchers in academia or industry.
Program
Discovery Grants Program - Individual
Recipient
Location
Ontario, Canada
Recipient Type
Academia
Type
Grant
Source
NSERC's Awards Data
As published
Application id
341852-2007
Name nom
Drummond, Christopher
Department département
Information Technology and Engineering, School of
Organization id
28
Institution établissement
University of Ottawa
Province en
Ontario
Province fr
Ontario
Country en
CANADA
Country fr
CANADA
Fiscal year exercice financier
2007
Competition year année de concours
2007
Award amount
14000
Program id
RGPIN
Program name en
Discovery Grants Program - Individual
Program name fr
Programme de subventions à la découverte - individuelles
Group en
Discovery grants programs
Group fr
Programmes de subventions à la découverte
Committee code
331
Committee name en
Computing and Information Sciences - B
Committee name fr
Informatique - B
Area of application code
801
Area of application group en
Information and communication services
Area of application group fr
Services d'information et de télécommunications
Area of application en
Computer software
Area of application fr
Logiciel
Research subject code
2805
Research subject group en
Artificial intelligence
Research subject group fr
Intelligence artificielle
Research subject en
Learning and inference theories
Research subject fr
Théories de l'apprentissage et l'inférence
Partie
1
Nb partie
5
Application title
Robust learning and evaluation with impoverished training data
Keyword
NA
Application summary
Being able to predict what will happen in the near future, with reasonable confidence, is an essential skill of humans and computers alike. Knowing what will come next allows people to plan ahead and use their resources efficiently and effectively. For computers to be useful tools, they must emulate this practice. Computers must plan ahead, predicting a user's needs and finding any items that may satisfy them.As with humans, computers can learn from past experience. But most research so far has assumed that the experience directly carries to the new problem. In recent times this assumption has become under increasing scrutiny. This project explores the impact of removing this assumption.If the change from past experience to a new problem is too large prior experience will not be useful. So some idea of the range and type of changes that a learning system will experience has be obtained. How well existing systems cope with these changes needs analyzing. This will lead to new variants of such algorithms or totally new algorithms that are robust to these changes.This proposal requests funds solely to support graduate students. It represents a good research topic for new researchers. Those trained in this area will have strong potential as researchers in academia or industry.