Incremental learning for recognizing handwritten characters using neural networks

Thesis/Dissertation · Sun Jan 01 04:00:00 EST 1989

OSTI ID:6047795

Klassen, M

Artificial Neural Networks (ANNs) are parallel distributed processing machines. The unique characteristics of ANNs are: Fault tolerance, robustness, plasticity and generalization. These offer great potential in many AI applications such as character recognition. Handwritten character recognition is an intrinsically interesting problem, but the difficulties of this task are the many variations in the characters. A robust new incremental learning method, which combines supervised and unsupervised learning paradigms implemented by the Functional Link Net, is illustrated with experimental results. Clustering, based on unsupervised learning, classifies the input data into several categories. The supervised learning paradigm then further classifies the data in the clustered categories.

• Research Organization: Case Western Reserve Univ., Cleveland, OH (USA)
• OSTI ID: 6047795
• Country of Publication: United States
• Language: English

Related Subjects

99 GENERAL AND MISCELLANEOUS
990200* -- Mathematics & Computers
ARTIFICIAL INTELLIGENCE
CLASSIFICATION
COMPUTERS
DATA
DATA PROCESSING
DIGITAL COMPUTERS
DISTRIBUTED DATA PROCESSING
EXPERIMENTAL DATA
FAULT TOLERANT COMPUTERS
INFORMATION
LEARNING
NEURAL NETWORKS
NUMERICAL DATA
PARALLEL PROCESSING
PATTERN RECOGNITION
PROCESSING
PROGRAMMING
USES