Abstract
Two-hidden-layer feedforward neural networks are investigated for the existence of an optimal hidden node ratio. In the experiments, the heuristic n1 =int (0.5nh + 1), where n1 is the number of nodes in the first hidden layer and nh is the total number of hidden nodes, found networks with generalisation errors, on average, just 0.023%-0.056% greater than those found by exhaustive search. This reduced the complexity of an exhaustive search from quadratic, to linear in , with very little penalty. Further reductions in search complexity to logarithmic could be possible using existing methods developed by the Authors
Original language | English |
---|---|
Title of host publication | Engineering Applications of Neural Networks. EANN 2016 |
Place of Publication | Switzerland |
Publisher | Springer International Publishing |
Pages | 253-266 |
Number of pages | 14 |
ISBN (Electronic) | 9783319441887 |
ISBN (Print) | 9783319441870 |
DOIs | |
Publication status | Published - 19 Aug 2016 |
Event | Engineering Applications of Neural Networks. EANN 2016 - Aberdeen, UK, 2-5 September, 2016 Duration: 19 Aug 2016 → … |
Publication series
Name | Communications in Computer and Information Sciences |
---|
Conference
Conference | Engineering Applications of Neural Networks. EANN 2016 |
---|---|
Period | 19/08/16 → … |
Bibliographical note
The final publication is available at link.springer.comKeywords
- Two-hidden-layer feedforward
- ANN
- Exhaustive search
- Optimal topology
- Optimal node ratio
- Heurix
- Universal function approximation
Fingerprint
Dive into the research topics of 'Accelerated Optimal Topology Search for Two-hidden-layer Neural Networks'. Together they form a unique fingerprint.Profiles
-
Robert Morgan
- Advanced Engineering Centre
- School of Arch, Tech and Eng - Professor of Thermal Propulsion Systems
Person: Academic