The following information was submitted:
Transactions: WSEAS TRANSACTIONS ON COMPUTERS
Transactions ID Number: 31-413
Full Name: Dominic Palmer-Brown
Position: Professor
Age: ON
Sex: Male
Address: School of Computing and Technology, University of East London, University Way, Docklands, E16 2RD
Country: UNITED KINGDOM
Tel: +44 (0)208 223 2170
Tel prefix:
Fax:
E-mail address: d.palmer-brown@uel.ac.uk
Other E-mails: dominicpalmer@hotmail.co.uk
Title of the Paper: Meta-adaptation: Neurons that change their mode
Authors as they appear in the Paper: Dominic Palmer-Brown, Sin Wee Lee, Chrisina Draganova, Miao Kang
Email addresses of all the authors: D.Palmer-brown@uel.ac.uk, S.W.Lee@uel.ac.uk, C.Draganova@uel.ac.uk, M.Kang@uel.ac.uk
Number of paper pages: 15
Abstract: This paper will explore the integration of learning modes into a single neural network structure in which layers of neurons and even individual neurons adopt different modes. There are several reasons to explore modal learning in neural networks. One motivation is to overcome the inherent limitations of any given mode (for example some modes memorise specific features, others average across features, and both approaches may be relevant according to the circumstances); another is inspiration from neuroscience, cognitive science and human learning, where it is impossible to build a serious model without consideration of multiple modes; and a third reason is non-stationary input data, or time-variant learning objectives, where the required mode is a function of time. Several modal learning ideas with an example application will be presented: The Snap-Drift Neural Network (SDNN) which toggles its learning between two modes, is incorporated into an on-line system to pro!
vide carefully targeted guidance and feedback to students; and an adaptive function neural network (ADFUNN), in which adaptation applies simultaneously to both the weights and the individual neuron activation functions. The combination of the two modal learning methods, in the form of Snap-drift ADaptive FUnction Neural Network (SADFUNN) is applied to optical and pen-based recognition of handwritten digits with results that demonstrate the effectiveness of the approach.
Keywords: Modal learning, Snap-drift, Diagnostic feedback, E-learning, Personalized learning, Multiple choice questions
EXTENSION of the file: .doc
Special (Invited) Session: WSEAS Neural Network Conference 2008
Organizer of the Session: I don't know but paper was an invited keynote at the conference
How Did you learn about congress: Library, Docklands Campus, University of East London, University Way, Docklands, London E16 2RD
IP ADDRESS: 161.76.125.97
