Unsupervised learnable neuron model with nonlinear interaction on dendrites

Todo, Yuki; Tamura, H.; Yamashita, Kazuya; Tang, Zheng

doi:10.1016/j.neunet.2014.07.011

Cited by 87 publications

(39 citation statements)

References 48 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The distinct characteristic of SDNM is that the sense of locality of dendrites can be represented and manipulated. For a specific given task, SDNM is able to identify what type of synapse (excitatory or inhibitory) is needed, where the synapse should be located, which branch of the dendrite is needed, and which one is not needed [42], [43]. This is realized by modeling the synaptic nonlinearity with a sigmoid function, and thus enabling the single neuron to be capable of computing linearly non-separable functions and approximating any complex continuous function [44], [45].…”

Section: Copyright C 2017 the Institute Of Electronics Information Amentioning

confidence: 99%

“…By taking the nonlinearity of synapses into consideration, a single dendritic neuron model (SDNM) has been proposed in our previous researches [42], [44], [45]. In [42], an unsupervised learning method was proposed for SDNM to learn two-dimensional eight-directionally selective problems.…”

Section: Single Dendritic Neuron Modelmentioning

confidence: 99%

“…In [42], an unsupervised learning method was proposed for SDNM to learn two-dimensional eight-directionally selective problems. In [44], an error back-propagation (BP) method was used for training SDNM to perform cancer classification tasks.…”

Section: Single Dendritic Neuron Modelmentioning

confidence: 99%

“…As mentioned before, the nonlinearity of synapses could be used to implement a type of multiplication instead of summation, thus our model adopts the multiplicative operation in the dendrite layer. It should be noted that a soft-minimization operator was utilized in our previous dendritic neuron model [42] to deal with binary input classification problem, while the multiplicative operation adopted in this study can address real number input problems. The multiplication is very equal to the logic AND operation as the value of inputs and outputs of the dendrites are either 1 or 0.…”

Section: Dendrite Layermentioning

confidence: 99%

See 3 more Smart Citations

Using a Single Dendritic Neuron to Forecast Tourist Arrivals to Japan

Chen

Sun

Gao

et al. 2017

IEICE Trans. Inf. & Syst.

Self Cite

View full text Add to dashboard Cite

SUMMARYWith the fast growth of the international tourism industry, it has been a challenge to forecast the tourism demand in the international tourism market. Traditional forecasting methods usually suffer from the prediction accuracy problem due to the high volatility, irregular movements and non-stationarity of the tourist time series. In this study, a novel single dendritic neuron model (SDNM) is proposed to perform the tourism demand forecasting. First, we use a phase space reconstruction to analyze the characteristics of the tourism and reconstruct the time series into proper phase space points. Then, the maximum Lyapunov exponent is employed to identify the chaotic properties of time series which is used to determine the limit of prediction. Finally, we use SDNM to make a short-term prediction. Experimental results of the forecasting of the monthly foreign tourist arrivals to Japan indicate that the proposed SDNM is more efficient and accurate than other neural networks including the multi-layered perceptron, the neuro-fuzzy inference system, the Elman network, and the single multiplicative neuron model.

show abstract

Section: Copyright C 2017 the Institute Of Electronics Information Amentioning

confidence: 99%

Section: Single Dendritic Neuron Modelmentioning

confidence: 99%

Section: Single Dendritic Neuron Modelmentioning

confidence: 99%

Section: Dendrite Layermentioning

confidence: 99%

See 2 more Smart Citations

Using a Single Dendritic Neuron to Forecast Tourist Arrivals to Japan

Chen

Sun

Gao

et al. 2017

IEICE Trans. Inf. & Syst.

Self Cite

View full text Add to dashboard Cite

show abstract

“…Without loss of generality, an assumption is used that there are nonlinear interactions among all of the inputs; thus, all of the inputs connect to all of the branches initially, and the ripened number of dendritic branches together with the locations and types of synapses on the dendritic branches are totally unknown and are synthesized through learning. This neuron model is successfully trained to learn the directionally selective problem and the depth rotation problem [51]- [57]. However, to simplify the computation, the authors have proposed to use simple multiplication and addition in place of the logical AND and OR to improve the algorithm [40].…”

Section: Neuron Model With Dendritic Nonlinearitymentioning

confidence: 99%

A Breast Cancer Classifier Using a Neuron Model with Dendritic Nonlinearity

Sha

Todo

et al. 2015

IEICE Trans. Inf. & Syst.

Self Cite

View full text Add to dashboard Cite

SUMMARYBreast cancer is a serious disease across the world, and it is one of the largest causes of cancer death for women. The traditional diagnosis is not only time consuming but also easily affected. Hence, artificial intelligence (AI), especially neural networks, has been widely used to assist to detect cancer. However, in recent years, the computational ability of a neuron has attracted more and more attention. The main computational capacity of a neuron is located in the dendrites. In this paper, a novel neuron model with dendritic nonlinearity (NMDN) is proposed to classify breast cancer in the Wisconsin Breast Cancer Database (WBCD). In NMDN, the dendrites possess nonlinearity when realizing the excitatory synapses, inhibitory synapses, constant-1 synapses and constant-0 synapses instead of being simply weighted. Furthermore, the nonlinear interaction among the synapses on a dendrite is defined as a product of the synaptic inputs. The soma adds all of the products of the branches to produce an output. A back-propagation-based learning algorithm is introduced to train the NMDN. The performance of the NMDN is compared with classic back propagation neural networks (BPNNs). Simulation results indicate that NMDN possesses superior capability in terms of the accuracy, convergence rate, stability and area under the ROC curve (AUC). Moreover, regarding ROC, for continuum values, the existing 0-connections branches after evolving can be eliminated from the dendrite morphology to release computational load, but with no influence on the performance of classification. The results disclose that the computational ability of the neuron has been undervalued, and the proposed NMDN can be an interesting choice for medical researchers in further research. key words: neuron model with dendritic nonlinearity, Wisconsin breast cancer database, back propagation neural networks, dendrite mechanisms

show abstract

A new recurrent pi‐sigma artificial neural network inspired by exponential smoothing feedback mechanism

Baş

Eğrioğlu

2022

Journal of Forecasting

View full text Add to dashboard Cite

Pi-sigma artificial neural networks have very good performance for forecasting problems because of their highly nonlinear model structure. Some time series can be forecasted better with the combination of simple and highly nonlinear structures. In this study, the architecture of the pi-sigma artificial neural network is modified by an inspiring exponential smoothing feedback mechanism. The architecture of the proposed neural network automatically balances simple and complex nonlinear model structures. Moreover, a training algorithm is created by using the sine cosine algorithm. The training algorithm has some solutions for overfitting and local optimum problems. The main contribution of the study is to propose a new hybrid recurrent neural network and its training algorithm. In the analysis of the new network's performance, the randomly selected eight subseries of the Financial Times Stock Exchange 100 Index daily time series between 2014 and 2018 are used. The performance of the proposed method is compared with popular deep learning artificial neural networks, pisigma artificial neural networks, and classical exponential smoothing methods. The statistical results show that the proposed method can produce better forecasting results than the others.

show abstract

Unsupervised learnable neuron model with nonlinear interaction on dendrites

Cited by 87 publications

References 48 publications

Using a Single Dendritic Neuron to Forecast Tourist Arrivals to Japan

Using a Single Dendritic Neuron to Forecast Tourist Arrivals to Japan

A Breast Cancer Classifier Using a Neuron Model with Dendritic Nonlinearity

A new recurrent pi‐sigma artificial neural network inspired by exponential smoothing feedback mechanism

Contact Info

Product

Resources

About