A review of learning in biologically plausible spiking neural networks

Taherkhani, Aboozar; Belatreche, Ammar; Li, Yuhua; Cosma, Georgina; Maguire, Liam; McGinnity, TM

doi:10.1016/j.neunet.2019.09.036

Cited by 249 publications

(117 citation statements)

References 117 publications

Supporting

Mentioning

101

Contrasting

Order By: Relevance

“…(2) Synaptic Weight According to formulas (3), (4), (5), (6), (7) and (8), it can be found that the noise stimulation can affect the firing moments interval between presynaptic and postsynaptic neurons Δt, and the weight of excitatory synapses g ex (t) and the weight of inhibitory synapses g in (t) is affected by Δt. Therefore, the change of the FR can lead to the change of synaptic weight.…”

Section: Plos Onementioning

confidence: 99%

“…Artificial neural network (ANN) is the theoretical and model basis of computational neuroscience, so it is significant to study the robustness of ANN based on brain-like intelligence. The spiking neural network (SNN) is the most biologically interpreted ANN, which can simulate the information processing of the biological brain network by establishing the nonlinear state dynamics behavior of neurons and the regulation process of synaptic weight dynamics [7,8]. Therefore, an SNN can process complex spatio-temporal information because of its powerful computing capacity [9][10][11].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Noise suppression ability and its mechanism analysis of scale-free spiking neural network under white Gaussian noise

Guo

Kan

et al. 2020

PLoS ONE

View full text Add to dashboard Cite

With the continuous improvement of automation and informatization, the electromagnetic environment has become increasingly complex. Traditional protection methods for electronic systems are facing with serious challenges. Biological nervous system has the self-adaptive advantages under the regulation of the nervous system. It is necessary to explore a new thought on electromagnetic protection by drawing from the self-adaptive advantage of the biological nervous system. In this study, the scale-free spiking neural network (SFSNN) is constructed, in which the Izhikevich neuron model is employed as a node, and the synaptic plasticity model including excitatory and inhibitory synapses is employed as an edge. Under white Gaussian noise, the noise suppression abilities of the SFSNNs with the high average clustering coefficient (ACC) and the SFSNNs with the low ACC are studied comparatively. The noise suppression mechanism of the SFSNN is explored. The experiment results demonstrate that the following. (1) The SFSNN has a certain degree of noise suppression ability, and the SFSNNs with the high ACC have higher noise suppression performance than the SFSNNs with the low ACC. (2) The neural information processing of the SFSNN is the linkage effect of dynamic changes in neuron firing, synaptic weight and topological characteristics. (3) The synaptic plasticity is the intrinsic factor of the noise suppression ability of the SFSNN.

show abstract

Section: Plos Onementioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Noise suppression ability and its mechanism analysis of scale-free spiking neural network under white Gaussian noise

Guo

Kan

et al. 2020

PLoS ONE

View full text Add to dashboard Cite

show abstract

“…The accumulation of input spikes fired at t 1 i and t 2 i is enough to produce an output spike at t 1 a whereas only the accumulation of input spikes fired at t 3 i and t 4 i is insufficient to produce an output spike at (12). w i finally increases, which is our desired adjustment.…”

Section: B the Selection And Computation Of Pair-spikementioning

confidence: 99%

“…Then, many researchers proposed a variety of precisely temporal encoding methods such as time to first spike, latency phase, and rank order [2]. Based on these encoding methods, spiking neuron modals can simulate biological neurons in the temporal dimension and have more biological plausibility than traditional neuron models [11], [12]. Composed of spiking neurons, spiking neural networks (SNNs) as a new generation of neural networks provide the stronger ability to approximate arbitrary continuous functions [12]- [14], and can process many complex spatio-temporal patterns well [15]- [19].…”

Section: Introductionmentioning

confidence: 99%

A Supervised Learning Algorithm for Spiking Neurons Using Spike Train Kernel Based on a Unit of Pair-Spike

Chen

Wang

2020

IEEE Access

View full text Add to dashboard Cite

In recent years, neuroscientists have discovered that the neural information is encoded by spike trains with precise times. Supervised learning algorithm based on the precise times for spiking neurons becomes an important research field. Although many existing algorithms have the excellent learning ability, most of their mechanisms still have some complex computations and certain limitations. Moreover, the discontinuity of spiking process also makes it very difficult to build an efficient algorithm. This paper proposes a supervised learning algorithm for spiking neurons using the kernel function of spike trains based on a unit of pair-spike. Firstly, we comprehensively divide the intervals of spike trains. Then, we construct an optimal selection and computation method of spikes based on the unit of pair-spike. This method avoids some wrong computations and reduces the computational cost by using each effective input spike only once in every epoch. Finally, we use the kernel function defined by an inner product operator to solve the computing problem of discontinue spike process and multiple output spikes. The proposed algorithm is successfully applied to many learning tasks of spike trains, where the effect of our optimal selection and computation method is verified and the influence of learning factors such as learning kernel, learning rate, and learning epoch is analyzed. Moreover, compared with other algorithms, all experimental results show that our proposed algorithm has the higher learning accuracy and good learning efficiency.

show abstract

“…[ 53 ] SNNs have become the third generation neural network model of future neural networks. It is more energy efficient than artificial neural networks (ANNs), and their size is much small, and low energy consumption, [ 56 ] similar to or even smaller than the biological nervous system. In recent years, many SNNs have been developed that mimic the actual functions of the biological nervous system through synaptic plasticity, spatiotemporal recognition, long‐ and short‐term memory, and so on.…”

Section: Introductionmentioning

confidence: 99%

The Future of Memristors: Materials Engineering and Neural Networks

Sun

Chen

Yan

2020

Adv Funct Materials

237

173

View full text Add to dashboard Cite

From Deep Blue to AlphaGo, artificial intelligence and machine learning are booming, and neural networks have become the hot research direction. However, due to the size limit of complementary metal–oxide–semiconductor (CMOS) transistors, von Neumann‐based computing systems are facing multiple challenges (such as memory walls). As the number of transistors required by the neural network increases, the development of neural networks based on the von Neumann computer is limited by volume and energy consumption. As the fourth basic circuit element, memristor shines in the field of neuromorphic computing. The new computer architecture based on memristor is widely considered as a substitute for the von Neumann architecture and has great potential to deal with the neural network and big data era challenge. This article reviews existing materials and structures of memristors, neurophysiological simulations based on memristors, and applications of memristor‐based neural networks. The feasibility and advancement of implementing neural networks using memristors are discussed, the difficulties that need to be overcome at this stage are put forward, and their development prospects and challenges faced are also discussed.

show abstract

A review of learning in biologically plausible spiking neural networks

Cited by 249 publications

References 117 publications

Noise suppression ability and its mechanism analysis of scale-free spiking neural network under white Gaussian noise

Noise suppression ability and its mechanism analysis of scale-free spiking neural network under white Gaussian noise

A Supervised Learning Algorithm for Spiking Neurons Using Spike Train Kernel Based on a Unit of Pair-Spike

The Future of Memristors: Materials Engineering and Neural Networks

Contact Info

Product

Resources

About