CNN based on multi-valued neuron as a model of associative memory for grey scale images

Aizenberg, Naum N.; Aizenberg, Igor

doi:10.1109/cnna.1992.274330

Cited by 104 publications

(84 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We first describe the complex-valued multistate neuron model used in this paper that is also used in [7,9,10]. In this model, the state and threshold of a neuron and the connection weights between the neurons are represented by complex values.…”

Section: Complex-valued Multistate Neural Networkmentioning

confidence: 99%

See 1 more Smart Citation

Complex-Valued Associative Memories with Projection and Iterative Learning Rules

Isokawa

Yamamoto

Nishimura

et al. 2018

Journal of Artificial Intelligence and Soft Computing Research

View full text Add to dashboard Cite

In this paper, we investigate the stability of patterns embedded as the associative memory distributed on the complex-valued Hopfield neural network, in which the neuron states are encoded by the phase values on a unit circle of complex plane. As learning schemes for embedding patterns onto the network, projection rule and iterative learning rule are formally expanded to the complex-valued case. The retrieval of patterns embedded by iterative learning rule is demonstrated and the stability for embedded patterns is quantitatively investigated.

show abstract

Section: Complex-valued Multistate Neural Networkmentioning

confidence: 99%

“…a phase value, in a complex plane [6,7,8,9,10]. This network can be used as an associative memory because some discrete values such as pixel values in an image can be mapped to the phase values and updates for neuron's state can be easily conducted.…”

Section: Introductionmentioning

confidence: 99%

Complex-Valued Associative Memories with Projection and Iterative Learning Rules

Isokawa

Yamamoto

Nishimura

et al. 2018

Journal of Artificial Intelligence and Soft Computing Research

View full text Add to dashboard Cite

show abstract

“…where 1 x , n x are the features of an instance, on which the performed function depends, and 0 ω , 1 ω , n ω are the weights. The values of the function and of the features are complex.…”

Section: Discrete Mvnmentioning

confidence: 99%

“…The discrete multi-valued neuron (MVN) was proposed by N. Aizenberg and I. Aizenberg in [1] for pattern classification. The neuron operates with complex-valued inputs, outputs, and weights.…”

Section: Introductionmentioning

confidence: 99%

Multi-Valued Neuron with Sigmoid Activation Function for Pattern Classification

Wu¹,

Chiou²,

Lee³

2014

JCC

View full text Add to dashboard Cite

Multi-Valued Neuron (MVN) was proposed for pattern classification. It operates with complex-valued inputs, outputs, and weights, and its learning algorithm is based on error-correcting rule. The activation function of MVN is not differentiable. Therefore, we can not apply backpropagation when constructing multilayer structures. In this paper, we propose a new neuron model, MVN-sig, to simulate the mechanism of MVN with differentiable activation function. We expect MVN-sig to achieve higher performance than MVN. We run several classification benchmark datasets to compare the performance of MVN-sig with that of MVN. The experimental results show a good potential to develop a multilayer networks based on MVN-sig.

show abstract

“…In particular, different kinds of neural networks are successfully used for solving the image recognition problem [21]. Neural networks based on multi-valued neurons have been introduced in [22] and further developed in [23][24][25][26]. Multi-valued neural element(MVN) is based on the ideas of multiple-valued threshold logic [27].…”

Section: Introductionmentioning

confidence: 99%

A Stochastic Dynamic Local Search Method for Learning Multiple-Valued Logic Networks

Cao¹,

Gao²,

Zhang³

et al. 2007

IEICE Transactions on Fundamentals of Electronics, Communicatio

View full text Add to dashboard Cite

SUMMARY In this paper, we propose a stochastic dynamic local search(SDLS) method for Multiple-Valued Logic (MVL)learning by introducing stochastic dynamics into the traditional local search method. The proposed learning network maintains some trends of quick descent to either global minimum or a local minimum, and at the same time has some chance of escaping from local minima by permitting temporary error increases during learning. Thus the network may eventually reach the global minimum state or its best approximation with very high probability. Simulation results show that the proposed algorithm has the superior abilities to find the global minimum for the MVL network learning within reasonable number of iterations.

show abstract

CNN based on multi-valued neuron as a model of associative memory for grey scale images

Cited by 104 publications

References 4 publications

Complex-Valued Associative Memories with Projection and Iterative Learning Rules

Complex-Valued Associative Memories with Projection and Iterative Learning Rules

Multi-Valued Neuron with Sigmoid Activation Function for Pattern Classification

A Stochastic Dynamic Local Search Method for Learning Multiple-Valued Logic Networks

Contact Info

Product

Resources

About