Parekh, Rajesh G., Yang, Jihoon and Honavar, Vasant G. (1997) Constructive Neural Network Learning Algorithms for Multi-Category Real-Valued Pattern Classification. Technical Report TR97-06, Department of Computer Science, Iowa State University.
Constructive Neural Network Learning Algorithms for Multi-Category
Real-Valued Pattern Classification
Rajesh Parekh, Jihoon Yang, and Vasant Honavar
Artificial Intelligence Research Group
Department of Computer Science
226 Atanasoff Hall
Iowa State University
Ames, IA 50011. U.S.A.
firstname.lastname@example.org, email@example.com, firstname.lastname@example.org
Constructive learning algorithms offer an attractive approach for
incremental construction of potentially near-minimal neural network
architectures for pattern classification tasks. These algorithms
help overcome the need for ad-hoc and often inappropriate choice
of network topology in the use of algorithms that search for a
suitable weight setting in an a-priori fixed network architecture.
Several such algorithms proposed in the literature have been shown
to converge to zero classification errors (under certain assumptions)
on finite, non-contradictory training sets in 2-category classification
tasks. The convergence proofs for each of these algorithms (with the
exception of the Upstart and the Perceptron Cascade) rely on the
assumption that the pattern attributes are either binary or bipolar
valued. This paper explores multi-category extensions of several
constructive neural network learning algorithms for classification
tasks where the input patterns may take on real-valued attributes.
In each case, we establish the convergence to zero classification
errors on a multi-category classification task. Results of experiments
with non-linearly separable multi-category datasets demonstrate the
feasibility of this approach and suggest several interesting directions
for future research.
Contact site administrator at: email@example.com