Application of Hopfield Network to Saccades
This work addresses scene analysis for applications like object representation and pattern recognition, but it appears incremental as it applies an existing Hopfield network to a new domain.
The authors tackled the problem of emulating human eye saccades for scene analysis by proposing a Hopfield neural network with an energy function for location and identification tasks, and computer simulations showed the network performs these tasks cooperatively, suggesting applicability to shift-invariant pattern recognition.
Human eye movement mechanisms (saccades) are very useful for scene analysis, including object representation and pattern recognition. In this letter, a Hopfield neural network to emulate saccades is proposed. The network uses an energy function that includes location and identification tasks. Computer simulation shows that the network performs those tasks cooperatively. The result suggests that the network is applicable to shift-invariant pattern recognition.