University of Tasmania
Browse
ARFN_Ollington_2003.pdf (247.77 kB)

Adaptive Response Function Neurons

Download (247.77 kB)
conference contribution
posted on 2023-05-26, 10:07 authored by Ollington, R, Vamplew, P
Biological neurons that show a locally tuned response to input may arise from the network topology of interneurons in the system. By considering such a subnetwork, a learning algorithm is developed for the online learning of the centre, width and shape of locally tuned response functions. The response function for each input is trained independently, resulting in a very good fit for the presented data. Two example networks utilising these neurons were considered. The first was a\ completely supervised network while the second utilised\ a Kohonen-like training scheme for the hidden layer. The\ adaptive response function neurons (ARFNs) were able\ to achieve excellent class separation while maintaining\ good generalisation with relatively few neurons.

History

Publication status

  • Published

Event title

2nd International Conference on Computational Intelligence, Robotics and Autonomous Systems

Event Venue

Singapore

Date of Event (Start Date)

2003-12-15

Date of Event (End Date)

2003-12-18

Repository Status

  • Open

Usage metrics

    University Of Tasmania

    Categories

    No categories selected

    Exports

    RefWorks
    BibTeX
    Ref. manager
    Endnote
    DataCite
    NLM
    DC