Gang-neuron
Remember to cite the original articles.
Paper 1: Dendrite Net: A White-Box Module for Classification, Regression, and System Identification
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.
https://www.bilibili.com/video/BV1Dp4y1a7Bk?pop_share=1
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。)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.
Correct:MNIST->MINIST
Paper 2: A Relation Spectrum Inheriting Taylor Series: Muscle Synergy and Coupling for Hand
http://arxiv.org/abs/2004.11910
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.
AI 3: It may be time to improve the neuron of artificial neural network
https://doi.org/10.36227/techrxiv.12477266 (IEEE preprints-You should cite it.)
AI 3 is for deep learning (CV,NLP). IEEE preprints ranking: Top 1 in yearly popularity
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
Interesting things: (1) The computational complexity of dendrite modules
One important thing: ResDD can replace the current all ANNs' Neurons (ResDD modules+ One Linear module)! ResDD has controllable precision for better generalization capability!
Contact me if you have problems in use.
E-mail: gangliu.6677@gmail.com