Disqus for deduction-theory

KihwanNet: A Platform for Creating a Neural Network in Real Time



KihwanNet is a Platform for creating a neural network in real time.



What I wanted to do



It took only 30 minutes to understand a concept of the perceptron, but it takes 2 hours to code one. (At least for the first time)




Reading about Convolution filter from Gimp manual is enough to understand the concept of CNN(Convolutional Neural Network), But to code one, I had to read more than ten of articles, papers and code samples.
Why is this so difficult?


If you are a programmer, you may know coding is mostly simple labor. Sometimes you just copy and paste all day long.


What creating a better program is a concept. It is based on what perspective you use to see the problems. It is also called philosophy.


Even so, there was no platform to try a new concept quicker and easier.   


CodePen writes HTML, CSS, and JavaScript and gets a real-time preview.



And, Scratch


I needed something like Codepen or Scratch for Neural Network research.   


So, I decided to create a new platform that people can try to implement their concept easier and proceed with it in the real time.   


True potential of perceptron

Perceptron has known as a function that can decide whether an input, represented by a vector of numbers, belongs to some specific class or not. It is from Wikipedia.   


But I’m telling you, Perceptron is not just ‘Linear classifier’.




When there is a sentence, first empty the part corresponding to a result information. Once you have empty the result information, you can infer relativity information and information structures. Then you can use this information structure to create another information. This explains how we can create an open information structure. In a case of “Five Ws and One H”, "who, when, where and what" describes a result information while "how and why" a relativity information.




We tried same inference method to see it is applied to a perceptron model. We've emptied an input and an output from a perceptron model that contains a result information. The information remains after is a network architecture and weights. This can act as a sentence structure or a rule of the game which is an open information structure.


We’ve found that perceptron not only can mimic characteristics of human’s way of thinking but create its own way of thinking because it does core logical action of creating an open information structure.


Yesterday’s trend: Bigger, Faster and Robustic

People are shaking their heads at the idea that AI will change society as they reconsider the industrial revolution without understanding the deep side of AI technology.


“As a machine has replaced many of the physical labor that humans do, AI will replace much of the intellectual labor that humans do.”
“In the future, AI will be able to classify, judge, and process more data faster than any human in the same time.”
“AI will not believe unnecessary emotional games that human plays, so will be more reliable and more accurate.”
etc.


I know that the current AI is not that level yet.
I do not know if AI will be this level in the future or when it will be this level.


To be honest, I don’t really care about this part.


KihwanNet is about changing the perspective

Watch your inside first.


Perceptron's greatest strength is that I can port my mind to computers. It is certainly easier and more likely to be able to train dogs to listen to me at this point.


Use KihwanNet’s easy interface to implement what you think is better and smarter.


Optimized for discovering, experimenting and creating new information structure

Thinking and expressing your thoughts can sometimes create unintended loopholes. This is not a bug or a bad thing, but rather a good opportunity to think about what I have in mind and what I need to do to improve it.


KihwanNet is a tool for developing ideas.


A well-known XOR solution


KihwanNet expresses the neural network intuitively and can understand the contents without looking at the numerical value.


An oscillator is a very important concept in information circuits.


Not all RNNs are Recurrent. For example, LTSM is strictly speaking a connected relay.
KihwanNet is suitable for studying the hidden concept inside it by making it from the simplest model directly.


Feedback Timer Circuit Using Recurrent


Share it, fork it and build a better one!



Share your information-processing mindset with others.



Work In Progress...

KihwanNet is currently under development.


Our research history



Support Us

If you like our article and would like to support us, please mining Monero below. If you press the START MINING button, your computer will work and support us in cryptocurrency. It's about a ten cents a day. For reference, set the SPEED lower to 80%, so your computer will not bother.
Support Us by Mining Monero.

I will not use sponsored currency for my personal use. I do not need extra money for my living. I am planning to sponsor a group home (nursery school) that cares for children and youth without parents. I am a computer programmer, and I have been doing free coding education activity called Rellat since 2016. I will use all of your sponsorship here.


Also, you can send us existing cryptocurrency.
Bitcoin: 1Jocrm8iKUtw4h19JttGLjj9ouQnDHrmpB
Monero: 45sQXZzqtFAKgJJgtQh3MuGYwUHHTb5bEZzvfdw3QhvSKpb1KMJmgnSQCVkWGcmL1PVzqVfV4bZH5D2C5uRfeWHLUf5pMkw

Facebook Comments

Disqus Comments

About Authors

Hello, I'm Kenneth Lee. I'm a business man who live in South Korea and America. I work in the software company "Deduction Theory, LLC" as CEO.
I work with my younger brother Chase Lee. We study Logic, Mathematics, Science, and computer information theory subject. This blog is for explaining the other people about our study.
We also working on an open source computer programming education project, Rellat. I'm looking for a translating volunteer for this project. I think this project will help many children, students, adults who are living in all around world, especially low income people. This project is free for everyone. It's designed for helping people. I will also make schools and orphanages in low income countries to teach the kids computer programming for they can have a better job.
Please visit the web page below that introduces Rellat project and tell me if you think that is worthy to give your help.
Introducing Rellat: Open Source and Open Study Project
There are Korean and English contents in this projects for translating to the other languages. I wrote all of them originally. So you can choose English or Korean from the original contents to translate whether you want.
We are opened to every language in the world. Thank you.
Hello. I'm Chase Lee. who is working on Rellat Project with Kenneth Lee.
When I was a child, I used to make animation with adobe flash program. Then I wanted to make a game with it, so I start coding with action script. That was the first time I started programming.
The methodology of Deduction Theory is the same as the way I do my usual work.
In fact, when I look at the code that goes over 500 lines, I have no sense and I can not remember all of them. Even these days, I still can not remember some of simple code syntax, so I often google it.
Instead, I keep track of what kind of thinking the code was made in, and what relativity information it uses. This is a coding methodology, a coding style or a computing perspective in Deduction Theory
By understanding how to think, you can compare how handling information better. This is the essence, and the most important thing.
The remaining space in the program can be filled by the power of Google and stack overflow.
I think you also can do a massive high-quality information processing by this way without confusing into new technologies and tens of thousands of lines of codes that are constantly being created.

Popular Posts

Visitor Map

Flag Counter