Multiplierless Implementation of Noisy Izhikevich Neuron With Low-Cost Digital Design

Haghiri, Saeed; Zahedi, Abdulhamid; Naderi, Ali; Ahmadi, Majid

doi:10.1109/tbcas.2018.2868746

Cited by 44 publications

(35 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In another research, authors have presented a Multiplier less Noisy Izhikevich Neuron (MNIN) model, which was used for digital implementation of Biological neural networks in large scale. Simulation results have shown that the MNIN model reproduces the same operations of the original noisy Izhikevich neuron [4]. In another paper, authors have performed numerical simulations of synaptically coupled Izhikevich networks under the effect of general non-Gaussian Lvy noise.…”

Section: Introductionmentioning

confidence: 99%

A Mathematical Model for the Signal of Death and Emergence of Mind Out of Brain in Izhikevich Neuron Model

Fioranelli¹,

Sepehri²,

Roccia³

et al. 2019

Open Access Maced J Med Sci

View full text Add to dashboard Cite

AIM:In this paper, using a mathematical model, we will show that for special exchanged photons, the Hamiltonian of a collection of neurons tends to a constant number and all activities is stopped. These photons could be called as the dead photons. To this aim, we use concepts of Bio-BIon in Izhikevich Neuron model.METHODS:In a neuron, there is a page of Dendrite, a page of axon’s terminals and a tube of Schwann cells, axon and Myelin Sheath that connects them. These two pages and tube form a Bio-Bion. In a Bio-Bion, exchanging photons and some charged particles between terminals of dendrite and terminals of axon leads to the oscillation of neurons and transferring information. This Bion produces the Hamiltonian, wave equation and action potential of Izhikevich Neuron model. Also, this Bion determines the type of dependency of parameters of Izhikevich model on temperature and frequency and obtains the exact shape of membrane capacitance, resting membrane potential and instantaneous threshold potential.RESULTS:Under some conditions, waves of neurons in this BIon join to each other and potential shrinks to a delta function. Consequently, total Hamiltonian of the system tends to a constant number and system of neuron act like a dead system. Finally, this model indicates that all neurons have the ability to produce similar waves and signals like waves of the mind.CONCLUSION:Generalizing this to biology, we can claim that neurons out of the brain can produce signals of minding and imaging and thus mind isn’t confined to the brain.

show abstract

Section: Introductionmentioning

confidence: 99%

A Mathematical Model for the Signal of Death and Emergence of Mind Out of Brain in Izhikevich Neuron Model

Fioranelli¹,

Sepehri²,

Roccia³

et al. 2019

Open Access Maced J Med Sci

View full text Add to dashboard Cite

show abstract

“…It is mentioned that in our proposed hardware, the LCU module is applied to calculates the power‐2 based function

Y_{n e w}

. In this case, we used the LCU module that is presented in Haghiri et al…”

Section: Digital Hardware Design (Dhd)mentioning

confidence: 99%

“…C, The proposed multiplierless implementation of

V_{C C}

. D, Hardware realization of the

Y_{n e w}

based on the LCU module [Colour figure can be viewed at wileyonlinelibrary.com]…”

Section: Digital Hardware Design (Dhd)mentioning

confidence: 99%

“…This approach is inspired by information processing in biological neural networks and makes them interesting choice for the efficient realization of biological neural networks . From the neuromorphic engineering point of view, hardware implementation of different parts of the central nervous system (CNS), including neurons, synapses, and astrocytes, is significant in this field …”

Section: Introductionmentioning

confidence: 99%

“…[3][4][5][6] From the neuromorphic engineering point of view, hardware implementation of different parts of the central nervous system (CNS), including neurons, synapses, and astrocytes, is significant in this field. [7][8][9][10] Neurons are the basic blocks in the brain that communicates with other neurons via connection ports called synapses. 11 In fact, the CNS is made of a large number of biological neurons in a complex pattern.…”

mentioning

confidence: 99%

See 2 more Smart Citations

Digital FPGA implementation of spontaneous astrocyte signalling

Haghiri

Ahmadi

2020

Circuit Theory & Apps

Self Cite

View full text Add to dashboard Cite

Astrocytes are the most abundant type of glial cells in the central nervous system (CNS). These non-neuronal cells are able to regulate the neurons activity in the different parts of brain tissue by calcium waves generation in its internal space.Moreover, astrocytes interact with neurons and modulate the spiking activity of them. In this paper, a set of piecewise linear estimations of a three-dimensional spontaneous astrocyte model are presented for digital FPGA realization. This leads to achieve a high-speed and low-cost system in large-scale implementation. In this approach, the three-dimensional original model is converted to a two-dimensional one and the hardware overhead have been reduced, significantly due to eliminating the large number of multiplications in the original astrocyte model. Simulation results in MATLAB demonstrate that our method can mimic the original calcium waves in high degree of similarity. To validate our method in case of hardware, the proposed model has been tested and simulated in Modelsim software and also implemented on Spartan3 XC3S50 (TQ144) FPGA board. Hardware realization results show that the proposed model has high similarity by the simulation outputs. Consequently, this reduced-model of astrocyte can be used in large-scale networks because of its low-cost hardware and high-speed system. KEYWORDS digital implementation, FPGA, neuron, spontaneous astrocyte INTRODUCTIONSpiking neural networks (SNNs) are very attractive research area that helps to investigate the neural networks, which is inspired by nature. 1,2 This approach is inspired by information processing in biological neural networks and makes them interesting choice for the efficient realization of biological neural networks. [3][4][5][6] From the neuromorphic engineering point of view, hardware implementation of different parts of the central nervous system (CNS), including neurons, synapses, and astrocytes, is significant in this field. [7][8][9][10] Neurons are the basic blocks in the brain that communicates with other neurons via connection ports called synapses. 11 In fact, the CNS is made of a large number of biological neurons in a complex pattern. In other words, the data transmission between two coupled neurons is completed via synaptic terminal. On the other hand, the non-neuronal astrocyte cells are connected to neurons and synapses to regulate and protect the spiking neurons activity during the synaptic coupling. 1,2,7 Also, the astrocytes generate the spontaneous oscillations in its internal space that is observed as calcium wave patterns in the cytosol. From a physiological viewpoint, neurons in the brain are surrounded by a large number of astrocytes (by 709 Int J Circ Theor Appl. 2020;48:709-723.wileyonlinelibrary.com/journal/cta

show abstract

Implementation of Izhikevich neuron based on stochastic computing using a novel inspired Omega‐Flip stochastic number generator

Hedayatpour

Karami

Shamsi

2022

Circuit Theory & Apps

View full text Add to dashboard Cite

This paper presents an optimized stochastic multiplier to implement Izhikevich spiking neuron model. A novel stochastic number generator is used as the main block for stochastic computing to design a stochastic multiplier. The designed multiplier was used to describe and implement Izhikevich neuron model equation which is capable to produce variant responses of spiking neurons. To the best of the author's knowledge, this work is the pioneer using a designed multiplier for computing all of the multiplication expressions in spiking neuron equation. The effect of increasing number of bit streams on the accuracy of stochastic computing is studied. Furthermore, some numerical intervals that are more prone to the error are found and illustrated upon stochastic computing usage, and a method is proposed to improve the error prone numerical intervals. In addition, the response accuracy is optimized by changing time step parameter in solving ordinary differential Izhikevich neuron model equation using Euler's method. Hence, a 13‐bit stochastic multiplier is designed. It is found that variations in parameters a and b have a profound effect on the accuracy of recovery variable u and, consequently, on the responses. Out of 20 responses of Izhikevich neuron model, 11 responses are generated using the proposed stochastic computing method and compared with piecewise linear method and some previous architectures of Izhikevich neuron model implementations.

show abstract

Multiplierless Implementation of Noisy Izhikevich Neuron With Low-Cost Digital Design

Cited by 44 publications

References 28 publications

A Mathematical Model for the Signal of Death and Emergence of Mind Out of Brain in Izhikevich Neuron Model

A Mathematical Model for the Signal of Death and Emergence of Mind Out of Brain in Izhikevich Neuron Model

Digital FPGA implementation of spontaneous astrocyte signalling

Implementation of Izhikevich neuron based on stochastic computing using a novel inspired Omega‐Flip stochastic number generator

Contact Info

Product

Resources

About