Fast Learning Neural Nets with Adaptive Learning Styles

There are many learning methods in artificial neural networks. Depending on the application, one
learning or weight update rule may be more suitable than another, but the choice is not always clear-cut, despite
some fundamental constraints, such as whether the learning is supervised or unsupervised. This paper addresses
the learning style selection problem by proposing an adaptive learning style. Initially, some observations
concerning the nature of adaptation and learning are discussed in the context of the underlying motivations for
the research, and this paves the way for the description of an example system. The approach harnesses the
complementary strengths of two forms of learning which are dynamically combined in a rapid form of
adaptation that balances minimalist pattern intersection learning with Learning Vector Quantization. Both
methods are unsupervised, but the balance between the two is determined by a performance feedback parameter.
The result is a data-driven system that shifts between alternative solutions to pattern classification problems
rapidly when performance is poor, whilst adjusting to new data slowly, and residing in the vicinity of a solution
when performance is good.

Citation:
Palmer-Brown, D. et al. (2003). “Fast Learning Neural Nets with Adaptive Learning Styles.” (Invited Paper). In Proceedings of the 17th European Simulation Multiconference (ESM'2003) Nottingham Trent University, Nottingham, UK, 9th - 11th June, pp. 118–123..