Gradient descent learning for quaternionic Hopfield neural networks
Introduction
Models of neural networks have been extended and applied in a variety of areas. Complex-valued neural networks have been one of the most successful extensions. Neural networks have currently been extended to quaternionic versions, such as multi-layered perceptrons and Hopfield neural networks (HNNs) [1], [2], [3], [4], [5], [6], [7], [8], [9], [10], [11], [12]. Moreover, quaternions have often been used in signal processing [13], [14].
An HNN is a recurrent neural network with mutual connections, and is one of the most successful neural network models. Complex-valued HNNs can represent phasor information, and have been applied to the storage of gray-scale images [15], [16]. To improve storage capacity and noise tolerance, several learning algorithms have been studied [17], [18], [19]. The projection rule is a fast learning algorithm, but is restricted by network topologies [20], [21], [22]. The gradient descent learning algorithm is iterative and flexible in network topologies, although its learning speed is slower [23], [24], [25].
Complex-valued HNNs have been extended to quaternionic HNNs (QHNNs). Several types of activation functions have been proposed for QHNNs. The split activation function is the simplest [26]. The multistate activation function has been applied to the storage of color images [27]. Attractors of QHNNs have also been studied, and a variety of network topologies have been proposed [28]. Bidirectional models with multistate activation function were found to improve noise tolerance [29]. A hybrid QHNN is a model with the split activation function. It improves noise tolerance by utilizing the non-commutativity of quaternions [30]. Thus far, the Hebbian learning rule and the projection rule have been studied. The Hebbian learning rule, however, is primitive, with very little storage capacity [30]. The projection rule, meanwhile, cannot be applied to hybrid QHNNs, because it requires fully left- or right-connections in QHNNs. In this study, we propose the gradient descent learning. Gradient descent learning is flexible in network topologies, and can be applied to hybrid QHNNs. Signal processing provides a novel technique, the GHR calculus [31], [32], [33]. Using the GHR calculus, gradient descent learning can be represented in an elegant form. We performed computer simulations to analyze storage capacity and noise tolerance. We show that either the QHNNs or hybrid QHNNs with gradient descent learning outperformed the QHNNs with projection rule.
This paper is organized as follows. Section 3 describes quaternions and QHNNs. In Section 3, gradient descent learning is provided. Section 5 describes the computer simulation and Section 5 discusses the results. Finally, Section 6 presents the conclusion.
Section snippets
Hopfield neural networks
An HNN is a model of a recurrent neural network, and consists of the neurons and symmetric mutual connections between neurons. A neuron receives the inputs from other neurons or sensors and produces a single output. The weighted sum models how the neuron copes with the inputs. In a quaternionic network, a neuron receives quaternions from the other neurons and produces a single quaternion as output. The strength of a connection is referred to as the connection weight. Neuron states and
Gradient descent learning for quaternionic Hopfield neural networks
We describe gradient descent learning for QHNNs. Let N and P be the number of neurons and training patterns, respectively. We denote the pth training pattern by . The learning determines the connection weights that make the training patterns stable.
First we determine the gradient descent learning for QHNNs. We define the error function E as is the weighted sum input to neuron c for the pth training pattern. Let η be a small
Computer simulations
We performed computer simulations to determine storage capacities and noise tolerance. In the simulations, we compared gradient descent learning and projection rule. The projection rule cannot be applied to hybrid QHNNs. We describe the initial weights and stopping condition for the gradient descent learning. The initial weights for gradient descent learning were zero. We confirmed whether all the training patterns were stable after the connection weights were updated. If they were stable, we
Discussion
First, let us consider the storage capacities. The storage capacity is how many training patterns the learning algorithm can successfully store for the given number of neurons. In this paper, we defined the maximal rate of the number of successfully stored random training patterns to that of neurons. The storage capacity of Hebbian learning rule was below 0.06N [30]. Those of hybrid QHNN and QHNN with gradient descent learning were approximate 0.6N and N, respectively. Therefore, gradient
Conclusions
In the present work, we proposed gradient descent learning and conducted computer simulations to investigate storage capacity and noise tolerance in QHNNs and hybrid QHNNs. The projection rule cannot be applied to hybrid QHNNs. In the case of QHNNs, the storage capacities of the projection rule and gradient descent learning were almost same. The storage capacity of hybrid QHNNs with gradient descent learning was smaller than those of the others. When the number of training patterns was
Masaki Kobayashi is a professor at University of Yamanashi. He received the B.S., M.S., and D.S. degrees in mathematics from Nagoya University in 1989, 1991, and 1996, respectively. He became a research associate and an associate professor at the University of Yamanashi in 1993 and 2006, respectively. He has been a professor since 2014.
References (34)
Complex-valued neural networks: theories and applications
Series on Innovative Intelligence
(2003)Complex-valued neural networks
Series on Studies in Computational Intelligence
(2012)Complex-valued neural networks: advances and applications
The IEEE Press Series on Computational Intelligence
(2013)Complex-valued Neural Networks: Utilizing High-dimensional Parameters
(2009)- et al.
Neural networks in multidimensional domains: fundamentals and new trends in modelling and control
Lecture Notes in Control and Information Sciences
(1998) - et al.
A scheme for counting pedestrians by quaternionic multilayer perceptron
Proceedings of the 14th International Symposium on Advanced Intelligent Systems
(2013) - et al.
Quaternion neural network and its application
Lect. Notes Artif. Intell.
(2003) A quaternary version of the back-propagation algorithm
Proceedings of IEEE International Conference on Neural Networks
(1995)An extension of the back-propagation algorithm to quaternions
Proceedings of International Conference on Neural Information Processing
(1996)- et al.
Twisted quaternary neural networks
IEEJ Trans. Elect. Electron. Eng.
(2012)
Uniqueness theorem for quaternionic neural networks
Signal Processing
Quaternion neural-network-based polSAR land classification in Poincare-sphere-parameter space
IEEE Trans. Geosci. Remote Sens.
Widely linear processing of hypercomplex signals
Proceedings of International Conference on Neural Information Processing (Lecture Notes in Computer Science)
Performance bounds of quaternion estimators
IEEE Trans. Neural Networks Learn. Syst.
Complex-valued multistate neural associative memory
IEEE Trans. Neural Networks
Complex-valued multistate associative memory with nonlinear multilevel functions for gray-level image reconstruction
IEEE Trans. Neural Networks
Pseudo-relaxation learning algorithm for complex-valued associative memory
Int. J. Neural Syst.
Cited by (0)
Masaki Kobayashi is a professor at University of Yamanashi. He received the B.S., M.S., and D.S. degrees in mathematics from Nagoya University in 1989, 1991, and 1996, respectively. He became a research associate and an associate professor at the University of Yamanashi in 1993 and 2006, respectively. He has been a professor since 2014.