Howells, G. and Fairhurst, M.C. and Bisset, D.L. (1995) BCN - A Novel Network Architecture for ram-Based Neurons. Pattern Recognition Letters, 16 (3). pp. 297-303. ISSN 0167-8655.
|The full text of this publication is not available from this repository. (Contact us about this Publication)|
A new architecture for networks of RAM-based Boolean neurons is presented which, whilst retaining learning and generalisation properties possessed by existing network architectures, allows for arbitrary target patterns for pattern classes with strong convergence properties. The network architecture provides the basis for a pattern recognition system capable of application in a practical environment.
|Uncontrolled keywords:||NEURAL NETWORKS; RAM-BASED NEURONS; FAST LEARNING|
|Subjects:||Q Science > QA Mathematics (inc Computing science) > QA 75 Electronic computers. Computer science|
|Divisions:||Faculties > Science Technology and Medical Studies > School of Computing|
|Depositing User:||P. Ogbuji|
|Date Deposited:||29 May 2009 11:19|
|Last Modified:||29 May 2012 09:08|
|Resource URI:||http://kar.kent.ac.uk/id/eprint/19608 (The current URI for this page, for reference purposes)|
- Depositors only (login required):