TY - GEN
T1 - Mahalanobis-based adaptive nonlinear dimension reduction
AU - Aouada, Djamila
AU - Baryshnikov, Yuliy
AU - Krim, Hamid
PY - 2010
Y1 - 2010
N2 - We define a new adaptive embedding approach for data dimension reduction applications. Our technique entails a local learning of the manifold of the initial data, with the objective of defining local distance metrics that take into account the different correlations between the data points. We choose to illustrate the properties of our work on the isomap algorithm. We show through multiple simulations that the new adaptive version of isomap is more robust to noise than the original non-adaptive one.
AB - We define a new adaptive embedding approach for data dimension reduction applications. Our technique entails a local learning of the manifold of the initial data, with the objective of defining local distance metrics that take into account the different correlations between the data points. We choose to illustrate the properties of our work on the isomap algorithm. We show through multiple simulations that the new adaptive version of isomap is more robust to noise than the original non-adaptive one.
UR - http://www.scopus.com/inward/record.url?scp=78149473894&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=78149473894&partnerID=8YFLogxK
U2 - 10.1109/ICPR.2010.187
DO - 10.1109/ICPR.2010.187
M3 - Conference contribution
AN - SCOPUS:78149473894
SN - 9780769541099
T3 - Proceedings - International Conference on Pattern Recognition
SP - 742
EP - 745
BT - Proceedings - 2010 20th International Conference on Pattern Recognition, ICPR 2010
T2 - 2010 20th International Conference on Pattern Recognition, ICPR 2010
Y2 - 23 August 2010 through 26 August 2010
ER -