Including Metric Space Topology in Neural Networks Training by Ordering Patterns | Zendy

Cezary Dendek | Zendy; Jacek Mańdziuk | Zendy

AI Assistant Blog Pricing

Home ZAIA Blog

Open Access

Including Metric Space Topology in Neural Networks Training by Ordering Patterns

Author(s) -

Cezary Dendek,

Jacek Mańdziuk

Publication year - 2006

Publication title -

lecture notes in computer science

Language(s) - English

Resource type - Book series

SCImago Journal Rank - 0.249

H-Index - 400

eISSN - 1611-3349

pISSN - 0302-9743

ISBN - 3-540-38871-0

DOI - 10.1007/11840930_67

Subject(s) - computer science , generalization , artificial neural network , metric (unit) , artificial intelligence , space (punctuation) , process (computing) , training (meteorology) , metric space , order (exchange) , topology (electrical circuits) , machine learning , theoretical computer science , mathematics , discrete mathematics , mathematical analysis , operations management , physics , combinatorics , meteorology , economics , operating system , finance

In this paper a new approach to the problem of ordering data in neural network training is presented. According to conducted research, generalization error visibly depends on the order of the training examples. Construction of an order gives some possibility to incorporate knowledge about structure of input and output space into the training process. Simulation results conducted for the isolated handwritten digit recognition problem confirmed the above claims.

The content you want is available to Zendy users.

Already have an account? Click here to sign in.

Having issues? You can contact us here

Accelerating Research