Dynamic Behavior of Artificial Hodgkin–Huxley Neuron Model Subject to Additive Noise

Kang, Qi; Huang, Bingyao; Zhou, MengChu

doi:10.1109/tcyb.2015.2464106

Cited by 51 publications

(14 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Instead of analog values, neurons within ventral stream use spikes to represent high level abstractions. To increase the level of realism in neural simulation, spiking neural network (SNN) [23], [24] is often used as the neural network modeling tool. For SNN, neuron model is essential since it defines how the activities of the neurons change in response to each other.…”

Section: Related Workmentioning

confidence: 99%

Event-Driven Continuous STDP Learning With Deep Structure for Visual Pattern Recognition

Liu

Yue

2019

IEEE Trans. Cybern.

View full text Add to dashboard Cite

Human beings can achieve reliable and fast visual pattern recognition with limited time and learning samples. Underlying this capability, ventral stream plays an important role in object representation and form recognition. Modeling the ventral steam may shed light on further understanding the visual brain in humans and building artificial vision systems for pattern recognition. The current methods to model the mechanism of ventral stream are far from exhibiting fast, continuous, and event-driven learning like the human brain. To create a visual system similar to ventral stream in human with fast learning capability, in this paper, we propose a new spiking neural system with an event-driven continuous spike timing dependent plasticity (STDP) learning method using specific spiking timing sequences. Two novel continuous input mechanisms have been used to obtain the continuous input spiking pattern sequence. With the event-driven STDP learning rule, the proposed learning procedure will be activated if the neuron receive one pre- or post-synaptic spike event. The experimental results on MNIST database show that the proposed method outperforms all other methods in fast learning scenarios and most of the current models in exhaustive learning experiments.

show abstract

Section: Related Workmentioning

confidence: 99%

Event-Driven Continuous STDP Learning With Deep Structure for Visual Pattern Recognition

Liu

Yue

2019

IEEE Trans. Cybern.

View full text Add to dashboard Cite

show abstract

“…In our proposed algorithm we utilized most traditional classification algorithms example decision tree (C4.5), 1-nearest neighbor rule (1-NN) and Naive Bayes (NB) etc [57][58][59][60][61][62], [63], [64], [28] as a base classifier learner or weak classifier. These classification algorithms are not achieved good results with imbalance dataset.…”

Section: Introductionmentioning

confidence: 99%

Rough Noise-Filtered Easy Ensemble for Software Fault Prediction

Riaz¹,

Ali²,

Jiao³

2018

Preprint

View full text Add to dashboard Cite

Software fault prediction is the very consequent research topic for software quality assurance. Data driven approaches provide robust mechanisms to deal with software fault prediction. However, the prediction performance of the model highly depends on the quality of dataset. Many software datasets suffers from the problem of class imbalance. In this regard, under-sampling is a popular data pre-processing method in dealing with class imbalance problem, Easy Ensemble (EE) present a robust approach to achieve a high classification rate and address the biasness towards majority class samples. However, imbalance class is not the only issue that harms performance of classifiers. Some noisy examples and irrelevant features may additionally reduce the rate of predictive accuracy of the classifier. In this paper, we proposed two-stage data pre-processing which incorporates feature selection and a new Rough set Easy Ensemble scheme. In feature selection stage, we eliminate the irrelevant features by feature ranking algorithm. In the second stage of a new Rough set Easy Ensemble by incorporating Rough K nearest neighbor rule filter (RK) afore executing Easy Ensemble (EE), named RKEE for short. RK can remove noisy examples from both minority and majority class. Experimental evaluation on real-world software projects, such as NASA and Eclipse dataset, is performed in order to demonstrate the effectiveness of our proposed approach. Furthermore, this paper comprehensively investigates the influencing factor in our approach. Such as, the impact of Rough set theory on noise-filter, the relationship between model performance and imbalance ratio etc. comprehensive experiments indicate that the proposed approach shows outstanding performance with significance in terms of area-under-the-curve (AUC).

show abstract

“…Furthermore, we derive and analyze the SNR gain for this type of signal. Extended theoretical investigations considering other neural models (e.g., the Hodgkin–Huxley and FitzHugh–Nagumo models) with different types of noises [ 34 , 35 ] is beyond the scope of this article.…”

Section: Introductionmentioning

confidence: 99%

Improvement of signal-to-noise ratio in parallel neuron arrays with spatially nearest neighbor correlated noise

Feng

Chen

et al. 2018

PLoS ONE

View full text Add to dashboard Cite

We theoretically investigate the signal-to-noise ratio (SNR) of a parallel array of leaky integrate-and-fire (LIF) neurons that receives a weak periodic signal and uses spatially nearest neighbor correlated noise. By using linear response theory, we derive the analytic expression of the SNR. The results show that the amplitude of internal noise can be increased up to an optimal value, which corresponds to a maximum SNR. Given the existence of spatially nearest neighbor correlated noise in the neural ensemble, the SNR gain of the collective ensemble response can exceed unity, especially for a negative correlation. This nonlinear collective phenomenon of SNR gain amplification may be related to the array stochastic resonance. In addition, we show that the SNR can be improved by varying the number of neurons, frequency, and amplitude of the weak periodic signal. We expect that this investigation will be useful for both controlling the collective response of neurons and enhancing weak signal transmission.

show abstract

Dynamic Behavior of Artificial Hodgkin–Huxley Neuron Model Subject to Additive Noise

Cited by 51 publications

References 33 publications

Event-Driven Continuous STDP Learning With Deep Structure for Visual Pattern Recognition

Event-Driven Continuous STDP Learning With Deep Structure for Visual Pattern Recognition

Rough Noise-Filtered Easy Ensemble for Software Fault Prediction

Improvement of signal-to-noise ratio in parallel neuron arrays with spatially nearest neighbor correlated noise

Contact Info

Product

Resources

About