Hypercomplex-Valued Recurrent Correlation Neural Networks
arXiv:2002.00027 · doi:10.1016/j.neucom.2020.12.034
Abstract
Recurrent correlation neural networks (RCNNs), introduced by Chiueh and Goodman as an improved version of the bipolar correlation-based Hopfield neural network, can be used to implement high-capacity associative memories. In this paper, we extend the bipolar RCNNs for processing hypercomplex-valued data. Precisely, we present the mathematical background for a broad class of hypercomplex-valued RCNNs. Then, we provide the necessary conditions which ensure that a hypercomplex-valued RCNN always settles at an equilibrium using either synchronous or asynchronous update modes. Examples with bipolar, complex, hyperbolic, quaternion, and octonion-valued RCNNs are given to illustrate the theoretical results. Finally, computational experiments confirm the potential application of hypercomplex-valued RCNNs as associative memories designed for the storage and recall of gray-scale images.
References in corpus (10)
- Applications of Clifford's Geometric Algebra
- Quaternion Gradient and Hessian
- Quaternion Involutions
- On a model of associative memory with huge storage capacity
- Quaternion Convolutional Neural Networks for Heterogeneous Image Processing
- Hopfield Networks is All You Need
- Large Associative Memory Problem in Neurobiology and Machine Learning
- On the Dynamics of Hopfield Neural Networks on Unit Quaternions
- A Broad Class of Discrete-Time Hypercomplex-Valued Hopfield Neural Networks
- An Introduction to Quaternion-Valued Recurrent Projection Neural Networks