Scaling Up Numerical Machine Learning

Thursday, November 14, 1996 - 9:30am
Keller 3-180
Chris Atkeson (Georgia Institute of Technology)
Numerical machine learning algorithms attempt to find structure in data. Approaches range from using parametric models such as neural networks to using non-parametric models. This talk will explore the differences between batch learning applications in which a fixed training set is used and continuous learning in which new data is continuously added to the training set.