Fastest learning in small world neural networks

Abstract

We investigate supervised learning in neural networks. We consider a multi-layered feed-forward network with back propagation. We find that the network of small-world connectivity reduces the learning error and learning time when compared to the networks of regular or random connectivity. Our study has potential applications in the domain of data-mining, image processing, speech recognition, and pattern recognition.

Text completely revised (14 pages), all new figures (7 figs)

References in corpus (9)

• Emergence of scaling in random networks
• Error and attack tolerance of complex networks
• Efficient Behavior of Small-World Networks
• The diameter of the world wide web
• The large-scale organization of metabolic networks
• Identity and Search in Social Networks
• Fast Response and Temporal Coding on Coherent Oscillations in Small-World Networks
• Harmony in the Small-World
• Critical brain networks

Cited by in corpus (5)

• Transient Dynamics of Sparsely Connected Hopfield Neural Networks with Arbitrary Degree Distributions
• Structural Pruning in Deep Neural Networks: A Small-World Approach
• Optimising the topology of complex neural networks
• Characterising brain network topologies: a dynamic analysis approach using heat kernels
• Reinforcement learning of recurrent neural network for temporal coding