Nonlinear Metric Learning with Kernel Density Estimation
Abstract:
Metric learning, the task of learning a good distance metric, is a key problem in machine learning
with ample applications. This paper introduces a novel framework for nonlinear metric learning,
called kernel density metric learning (KDML), which is easy to use and provides nonlinear,
probability-based distance measures. KDML constructs a direct nonlinear mapping from the
original input space into a feature space based on kernel density estimation. The nonlinear
mapping in KDML embodies established distance measures between probability density
functions, and leads to accurate classification on datasets for which existing linear metric
learning methods would fail. It addresses the severe challenge to distance-based classifiers when
features are from heterogeneous domains and, as a result, the Euclidean or Mahalanobis distance
between original feature vectors is not meaningful. We also propose two ways to determine the
kernel bandwidths, including an adaptive local scaling approach and an integrated optimization
algorithm that learns the Mahalanobis matrix and kernel bandwidths together. KDML is a
general framework that can be combined with any existing metric learning algorithm. As
concrete examples, we combine KDML with two leading metric learning algorithms, large
margin nearest neighbors (LMNN) and neighborhood component analysis (NCA). KDML can
naturally handle not only numerical features, but also categorical ones, which is rarely found in
previous metric learning algorithms. Extensive experimental results on various datasets show
that KDML significantly improves existing metric learning algorithms in terms of classification
accuracy.
Existing system:
Distance metrics are distance measurements between data points, such as Euclidean distance or
Manhattan distance. Learning a distance metric is a fundamental problem in machine learning
and data mining [1]. In many applications, once we have defined a good distance or similarity
measure between all pairs of data points, the data mining tasks would become trivial. For
example, with a perfect distance metric, the k-nearest neighbor (kNN) algorithm can achieve
perfect classification . As a result, ever since metric learning is proposed by Xing et al. [5], there
has been extensive research in this are. These new methods greatly improved the performance of
many metric-based algorithms and gained lots of popularity.
Proposed system:
Further Details Contact: A Vinay 9030333433, 08772261612
Email: info@takeoffprojects.com | www.takeoffprojects.com
We also propose two ways to determine the kernel bandwidths, including an adaptive local
scaling approach and an integrated optimization algorithm that learns the Mahalanobis matrix
and kernel bandwidths together. KDML is a general framework that can be combined with any
existing metric learning algorithm. As concrete examples, we combine KDML with two leading
metric learning algorithms, large margin nearest neighbors (LMNN) and neighborhood
component analysis (NCA). KDML can naturally handle not only numerical features, but also
categorical ones, which is rarely found in previous metric learning algorithms. Extensive
experimental results on various datasets show
that KDML significantly improves existing metric learning algorithms in terms of classification
accuracy.
SYSTEM REQUIREMENTS:
HARDWARE REQUIREMENTS:
System
:
Pentium IV 2.4 GHz.
Hard Disk
:
40 GB.
Floppy Drive
:
Monitor
1.44 Mb.
:
Mouse
:
Ram
15 VGA Colour.
Logitech.
:
512 Mb.
SOFTWARE REQUIREMENTS:
Operating system
:
Windows XP/7.
Coding Language
:
JAVA/J2EE
IDE
:
Netbeans 7.4
Database
:
MYSQL
Further Details Contact: A Vinay 9030333433, 08772261612
Email: info@takeoffprojects.com | www.takeoffprojects.com
Further Details Contact: A Vinay 9030333433, 08772261612
Email: info@takeoffprojects.com | www.takeoffprojects.com