Deep Learning in an Adaptive Function Neural Network

Conference paper


Palmer-Brown, Dominic and Kang, Miao 2006. Deep Learning in an Adaptive Function Neural Network. Proceedings of the AC&T, pp. 78-83
AuthorsPalmer-Brown, Dominic and Kang, Miao
TypeConference paper
Abstract

Artificial neural network learning is typically accomplished via adaptation between
neurons. This paper describes adaptation that is simultaneously between and within neurons. The
conventional neurocomputing wisdom is that by adapting the pattern of connections between neurons
the network can learn to respond differentially to classes of incoming patterns. The success of this
approach in an age of massively increasing computing power that has made high speed
neurocomputing feasible on the desktop and more recently in the palm of the hand, has resulted in
little attention being paid to the implications of adaptation within the individual neurons. The
computational assumption has tended to be that the internal neural mechanism is fixed. However,
there are good computational and biological reasons for examining the internal neural mechanisms of
learning. Recent neuroscience suggests that neuromodulators play a role in learning by modifying the
neuron’s activation function [Scheler] and with an adaptive function approach it is possible to learn
linearly inseparable problems fast, even without hidden nodes. The ADaptive FUction Neural
Network (ADFUNN) presented in this paper is based on a linear piecewise neuron activation function
that is modified by a novel gradient descent supervised learning algorithm [Palmer-Brown;Kang]. It
has been applied to the Iris dataset, and a natural language phrase recognition problem, exhibiting
impressive generalisation classification ability with no hidden neurons.

Keywordsneurocomputing; ADaptive FUction Neural Network (ADFUNN)
Year2006
ConferenceProceedings of the AC&T, pp
Publisher's version
License
CC BY-ND
Publication dates
Print2006
Publication process dates
Deposited09 Jun 2010
ISSN0-9550008-1-5
Web address (URL)http://www.uel.ac.uk/act/proceedings/documents/ACT06Proceeding.pdf
http://hdl.handle.net/10552/796
Additional information

Citation:
Palmer-Brown, D. and Kang, M. (2006) ‘Deep Learning in an Adaptive Function Neural Network’ Proceedings of the AC&T, pp.78-83..

Permalink -

https://repository.uel.ac.uk/item/8679x

Download files


Publisher's version
  • 38
    total views
  • 56
    total downloads
  • 1
    views this month
  • 0
    downloads this month

Export as