Gang-neuron

+ As long as you cite it in accordance with the specification, you can use gang neuron in your paper at will. 
+ 只要您规范引用，在您的文章中，您可以随便用！

Remember to cite the original papers, especially this paper: Liu, Gang (2020): It may be time to improve the neuron of artificial neural network.IEEE TechRxiv. https://doi.org/10.36227/techrxiv.12477266

If you use the content in https://doi.org/10.36227/techrxiv.12477266 without citing it, Gang will definitely defend his rights.

记得引用原文，尤其是这篇最核心论文:Liu, Gang (2020): It may be time to improve the neuron of artificial neural network. IEEE TechRxiv. https://doi.org/10.36227/techrxiv.12477266

-------------------Papers---------------------------------------------------------------------------------------------

Main Paper(AI): It may be time to improve the neuron of artificial neural network(IEEE TechRxiv, This paper is the IEEE TechRxiv Top 1 in yearly popularity.You Must cite it!)

https://doi.org/10.36227/techrxiv.12477266 (IEEE preprints-You should cite it.)

**Citation format: Liu, Gang (2020): It may be time to improve the neuron of artificial neural network. IEEE TechRxiv. https://doi.org/10.36227/techrxiv.12477266 **

IEEE preprints ranking: Top 1 in yearly popularity

The paper has been cited in multiple papers, such as IEEE Transactions on Cybernetics and IEEE Transactions on Neural Systems and Rehabilitation Engineering， on Google Scholar.

How to avoid curse of dimensionality(DD:normalization,0.99^∞≈0) :https://zhuanlan.zhihu.com/p/269306977

Artificial neural networks (ANNs) have won numerous contests in pattern recognition, machine learning, or artificial intelligence in recent years. The neuron of ANNs was designed by the stereotypical knowledge of biological neurons 70 years ago. Artificial Neuron is expressed as $f(wx+b)$ or $f(WX)$. This design does not consider dendrites' information processing capacity. However, some recent studies show that biological dendrites participate in the pre-calculation of input data. Concretely, biological dendrites play a role in extracting the interaction information among inputs (features). Therefore, it may be time to improve the neuron of ANNs. This paper adds the dendrites' function to artificial Neuron. The dendrite function can be expressed as $W^{i,i-1}A^{i-1} \circ A^{0|1|2|...|i-1}$ . The generalized new neuron can be expressed as $f(W(W^{i,i-1}A^{i-1} \circ A^{0|1|2|...|i-1}))$. The simplified new neuron be expressed as $f(\sum(WA \circ X))$ . After improving the neuron, there are so many networks to try. This paper shows some basic architecture for reference in the future.

Interesting things: (1) The computational complexity of dendrite modules $(W^{i,i-1}A^{i-1} \circ A^{i-1} )$ connected in series is far lower than Horner's method. Will this speed up the calculation of basic functions in computers? (2) The range of sight of animals has a gradient, but the convolution layer does not have this characteristic. This paper proposes receptive fields with a gradient. (3) The networks using Gang neurons can delete traditional networks' Fully-connected Layer. In other words, the Fully-connected Layers' parameters are assigned to a single neuron, which reduces the parameters of a network for the same mapping capacity.

One important thing: ResDD can replace the current all ANNs' Neurons (ResDD modules+ One Linear module)! ResDD has controllable precision for better generalization capability!

Paper 2: Dendrite Net: A White-Box Module for Classification, Regression, and System Identification(IEEE Transactions on Cybernetics, Top Journal,IF=19.118)

Citation format: G. Liu and J. Wang, "Dendrite Net: A White-Box Module for Classification, Regression, and System Identification," in IEEE Transactions on Cybernetics, doi: 10.1109/TCYB.2021.3124328.

https://doi.org/10.1109/TCYB.2021.3124328

ArXiv:https://arxiv.org/abs/2004.03955

DD can be used for generalized engineering.

This paper presents a basic machine learning algorithm, named Dendrite Net or DD, just like Support Vector Machine (SVM) or Multilayer Perceptron (MLP). DD's main concept is that the algorithm can recognize this class after learning, if the output's logical expression contains the corresponding class's logical relationship among inputs (and∖or∖not) .

Experiments and results:

DD, the first white-box machine learning algorithm, showed excellent system identification performance for the black-box system.
It was verified by nine real-world applications that DD brought better generalization capability relative to MLP architecture that imitated neurons' cell body (Cell body Net) for regression.
By MNIST and FASHION-MNIST datasets, it was verified that DD showed higher testing accuracy under greater training loss than Cell body Net for classification. The number of modules can effectively adjust DD's logical expression capacity, which avoids over-fitting and makes it easy to get a model with outstanding generalization capability.
Repeated experiments in MATLAB and PyTorch (Python) demonstrated that DD was faster than Cell body Net both in epoch and forward-propagation.

We highlight DD's white-box attribute, controllable precision for better generalization capability, and lower computational complexity. Not only can DD be used for generalized engineering, but DD has vast development potential as a module for deep learning.

__B站视频讲解（为了避免用词问题，我说的是中文。有中文基础的研究人员可以观看。）https://www.bilibili.com/video/BV1Dp4y1a7Bk?pop_share=1 __

DD is a new basic algorithm. If you find an algorithm similar to DD, please contact me. You may have misunderstood. Based on previous experience, new things are easy to be questioned.

I will explain to you, and I believe you will agree with me.

Good DD are eager to be asked. I like the discussions very much.

Use it and you will find it is great.

Paper 3: A Relation Spectrum Inheriting Taylor Series: Muscle Synergy and Coupling for Hand (Frontiers of Information Technology & Electronic Engineering, **工程院院刊）

This paper has been accepted by Frontiers of Information Technology & Electronic Engineering(FITEE)——Journal of Chinese Academy of Engineering, Q2. （我想发个**工程院的SCI期刊，所以选择了它。推荐本刊，期刊定位高，潜力大。）

**Citation format: Liu, G., Wang, J. A relation spectrum inheriting Taylor series: muscle synergy and coupling for hand. Front Inform Technol Electron Eng 23, 145–157 (2022). https://doi.org/10.1631/FITEE.2000578

Relation Spectrum can be used to "read" DD. (generalized engineering)

There are two famous function decomposition methods in math: Taylor Series and Fourier Series. Fourier series developed into Fourier spectrum, which was applied to signal decomposition\analysis. However, because the Taylor series whose function without a definite functional expression cannot be solved, Taylor Series has rarely been used in engineering. Here, we developed Taylor series by our Dendrite Net, constructed a relation spectrum, and applied it to model or system decomposition\analysis. The relation spectrum makes the online model human-readable, which unifies online performance and offline results.

Paper 4: EEGG: An analytic brain-computer interface algorithm (IEEE Transactions on Neural Systems and Rehabilitation Engineering,Top Journal in BCI)

**Citation format: G. Liu and J. Wang, "EEGG: An Analytic Brain-computer Interface Algorithm," in IEEE Transactions on Neural Systems and Rehabilitation Engineering, doi: 10.1109/TNSRE.2022.3149654.

http://dx.doi.org/10.1109/TNSRE.2022.3149654

Paper 5: XXXXXXXXXXX letter XXXXXX

Contact me if you have problems in use.

E-mail: gangliu.6677@gmail.com

LICENCE：CC BY-NC-SA 4.0

Paper： It may be time to improve the neuron of artificial neural network

The original 2020 paper（https://doi.org/10.36227/techrxiv.12477266） has been cited in multiple papers, such as IEEE Transactions on Cybernetics and IEEE Transactions on Neural Systems and Rehabilitation Engineering， on Google Scholar.

谷歌学术上可查到，原始的2020年论文( https://doi.org/10.36227/techrxiv.12477266 )已被IEEE Transactions on Cybernetics、IEEE Transactions on Neural Systems and Rehabilitation Engineering等期刊的多篇论文引用。

liugang1234567/Gang-neuron