A Method for Evaluating Chimeric Synchronization of Coupled Oscillators and Its Application for Creating a Neural Network Information Converter

Velichko, Andrei

doi:10.3390/electronics8070756

Cited by 12 publications

(13 citation statements)

References 47 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A significant advantage of pulsed signals is the availability of diverse methods for information encoding and synchronization. Methods of information encoding in ONN have been intensively developed, and the academic authors actively contribute to the development of new synchronization assessment techniques [12,16]. The simple burst oscillator circuits, presented in the current paper, can be of applied interest for the development of spike and oscillatory neural networks.…”

Section: Discussionmentioning

confidence: 99%

“…Equations (1) and (2) characterize the switch element and which state is determined by the voltage on the element (Figure 2b). We have already used a similar equation for modeling and analyzing experimental data on the dynamics of VO 2 oscillators [16]. If both branches are approximated by straight lines with differential resistances Roff and Ron, the model I-V characteristic has the form…”

Section: S-type Switch Models Controlled By Current and Voltagementioning

confidence: 99%

“…In contrast to the system of FitzHugh-Rinzel in Equation 9, Equations (16) and (17) use the direct I sw (U), and not the inverse I-V characteristic U sw (I), which is a two-valued, discontinuous function. Therefore, mathematical models of these circuits, most likely do not have an analytical solution, cannot be analyzed, and have only a numerical solution.…”

Section: Alternative Neural-like Circuits Based On a Switching S-elementmentioning

confidence: 99%

See 2 more Smart Citations

Switch Elements with S-Shaped Current-Voltage Characteristic in Models of Neural Oscillators

Борисков

Velichko

2019

Electronics

View full text Add to dashboard Cite

In this paper, we present circuit solutions based on a switch element with the S-type I–V characteristic implemented using the classic FitzHugh–Nagumo and FitzHugh–Rinzel models. Using the proposed simplified electrical circuits allows the modeling of the integrate-and-fire neuron and burst oscillation modes with the emulation of the mammalian cold receptor patterns. The circuits were studied using the experimental I–V characteristic of an NbO2 switch with a stable section of negative differential resistance (NDR) and a VO2 switch with an unstable NDR, considering the temperature dependences of the threshold characteristics. The results are relevant for modern neuroelectronics and have practical significance for the introduction of the neurodynamic models in circuit design and the brain–machine interface. The proposed systems of differential equations with the piecewise linear approximation of the S-type I–V characteristic may be of scientific interest for further analytical and numerical research and development of neural networks with artificial intelligence.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: S-type Switch Models Controlled By Current and Voltagementioning

confidence: 99%

Section: Alternative Neural-like Circuits Based On a Switching S-elementmentioning

confidence: 99%

See 1 more Smart Citation

Switch Elements with S-Shaped Current-Voltage Characteristic in Models of Neural Oscillators

Борисков

Velichko

2019

Electronics

View full text Add to dashboard Cite

show abstract

“…An alternative approach to reduce the number of trained weights is based on physical reservoir computing (RC) [23]. RC uses complex physical dynamic systems (coupled oscillators [24][25][26], memristor crossbar arrays [27], opto-electronic feedback loop [28]), or recurrent neural networks (echo state networks (ESNs) [29] and liquid state machines (LSMs) [30]), as reservoirs with rich dynamics and powerful computing capabilities. The couplings in the reservoir are not trained, but are specified in a special way.…”

Section: Introductionmentioning

confidence: 99%

Neural Network for Low-Memory IoT Devices and MNIST Image Recognition Using Kernels Based on Logistic Map

Velichko

2020

Electronics

View full text Add to dashboard Cite

This study presents a neural network which uses filters based on logistic mapping (LogNNet). LogNNet has a feedforward network structure, but possesses the properties of reservoir neural networks. The input weight matrix, set by a recurrent logistic mapping, forms the kernels that transform the input space to the higher-dimensional feature space. The most effective recognition of a handwritten digit from MNIST-10 occurs under chaotic behavior of the logistic map. The correlation of classification accuracy with the value of the Lyapunov exponent was obtained. An advantage of LogNNet implementation on IoT devices is the significant savings in memory used. At the same time, LogNNet has a simple algorithm and performance indicators comparable to those of the best resource-efficient algorithms available at the moment. The presented network architecture uses an array of weights with a total memory size from 1 to 29 kB and achieves a classification accuracy of 80.3–96.3%. Memory is saved due to the processor, which sequentially calculates the required weight coefficients during the network operation using the analytical equation of the logistic mapping. The proposed neural network can be used in implementations of artificial intelligence based on constrained devices with limited memory, which are integral blocks for creating ambient intelligence in modern IoT environments. From a research perspective, LogNNet can contribute to the understanding of the fundamental issues of the influence of chaos on the behavior of reservoir-type neural networks.

show abstract

“…Besides this, the possibility of using high-order synchronized states in reservior computing is also demonstrated recently in the Refs. [16,17,18,19,20].…”

Section: Introductionmentioning

confidence: 99%

High-order synchronization in a system of nonlinearly coupled Stuart-Landau oscillators

Thomas¹,

Karthiga²,

Senthilvelan³

2021

Preprint

View full text Add to dashboard Cite

The high-order synchronization was studied in systems driven by external force and in autonomous systems with proper frequency mismatch. Differing from the literature, in this article, we demonstrate the occurrence of high-order (1 : 2) synchronization in an autonomous nonlinearly coupled (Stuart-Landau) oscillators which admit a particular form of rotational symmetry. Interestingly, the observed 1 : 2 synchronization happens not only for a particular choice of natural frequencies but for all possible choices of frequencies. We have observed such a behaviour in the case of 1 : 1 synchronization, where we have seen a variety of couplings in the literature that forces the oscillators to have almost equal frequencies and makes the system to oscillate with a common frequency independent of whether the oscillators are identical or non-identical. Similarly, in this article we observe that, whether the initial choice of frequencies is of the ratio 1 : 2 or not, the given nonlinear coupling forces the system to oscillate with the frequency ratio 1 : 2. Further, we present synchronization and other dynamical behaviours of the system by considereing different choices of natural frequencies.

show abstract

A Method for Evaluating Chimeric Synchronization of Coupled Oscillators and Its Application for Creating a Neural Network Information Converter

Cited by 12 publications

References 47 publications

Switch Elements with S-Shaped Current-Voltage Characteristic in Models of Neural Oscillators

Switch Elements with S-Shaped Current-Voltage Characteristic in Models of Neural Oscillators

Neural Network for Low-Memory IoT Devices and MNIST Image Recognition Using Kernels Based on Logistic Map

High-order synchronization in a system of nonlinearly coupled Stuart-Landau oscillators

Contact Info

Product

Resources

About