Great Country Academician

While HiSilicon and Huaxin were busy designing and making chip breakthroughs, Xu Chuan was also studying mathematical problems related to chip design in the villa.

NPU neural network architecture is an emerging computer field compared to CPU architecture and GPU architecture.

It was first proposed by psychologists and neurobiologists and applied to computers by simulating the structure and computing methods of nerve cells in the human body or other living brains.

Compared with the original flat computing architecture, the neural network architecture is more similar to the 3D nature and can often provide a relatively simpler method when solving complex problems.

Therefore, neural network architecture has attracted more and more attention from the computer industry in recent years.

HiSilicon and Huaxin chose this area to make breakthroughs. On the one hand, they wanted to overtake in corners, but on the other hand, they had no choice.

There is no way. Compared with those Western countries and companies, China started too late in basic research on CPU architecture and GPU architecture, and is far less than the rich experience and strength of others.

Of course, there are also the most critical patents.

Relying on the moat of patents, Western companies such as Qualcomm, Apple, and Google have almost completely monopolized this field.

If you want to get around it, you have to find another way.

This is also the reason why HiSilicon and Huaxin choose to start with the NPU neural network architecture.

Although this architecture is still developed from the ARM architecture studied by ARM, it can lay a solid foundation for future independent research and development.

Looking through the information on the computer, Xu Chuan studied and analyzed it carefully.

Generally speaking, neural network architecture mainly uses various mathematical models to describe and simulate biological nervous systems at different levels from different perspectives.

Representative network models include BP network, RBF network, Hopfield network, self-organizing feature map network, etc.

Compared with traditional CPU architecture and GPU architecture, it is faster for him to start with this architecture.

After all, mathematical models and modeling, as well as the mathematical formulas behind them, are one of his research areas.

For example, the RBF neural network architecture (radial basis function network architecture) is a type of forward network constructed based on function approximation theory.

The learning of this type of network is equivalent to finding the best fitting plane for training data in a multi-dimensional space. The activation function of each hidden layer neuron of its radial basis function network constitutes a basis function of the fitting plane.

Explained using mathematical theory, the principle is actually very simple.

That is, search for a certain function g in a selected type of function, so that it is an approximate representation of a known function in a certain sense, and find the error caused by the approximate representation of g. "

This is one of the functional foundations of high school mathematics.

For Xu Chuan, studying these things was just to solve the problems of HiSilicon and Huaxin at the beginning, but as time went by, he became more and more interested in this kind of neural network.

This structure, which starts from mathematical mechanisms and uses models to complete different levels of description and simulation, has many applications in other fields besides chips.

Such as artificial intelligence, automatic control, robotics, statistics, etc.

These are areas that Xu Chuan is very interested in.

Needless to say, artificial intelligence is the future development trend.

Automatic control and robots are one of the core key points in the progress of social productivity.

As for statistics, it seems that it is an applied mathematics mainly for work in other fields.

But in fact, it itself can also be applied in the field of mathematics.

Of course, what he values ​​more is the use of neural networks to collect statistics and analyze data in the field of high-energy physics or materials science.

The latter two have quite large amounts of data and require more robust and simple mathematical statistics and analysis methods.

And after studying these days, Xu Chuan keenly feels that this kind of neural network seems to be more suitable for quantum chips and quantum computers than ordinary silicon-based chips for computers.

If the traditional silicon-based chip-based computer is considered to be 2D or 2.5D, then the quantum computer is 3D, inherently transcending one level in dimension.

As for the neural network computing method, it can actually be seen from a biological perspective that it is inherently a 3D three-dimensional structure.

Of course, this statement may be somewhat inaccurate.

But he does think it might be more adaptable to quantum computers.

It's just that there is currently no quantum computer that is fully available to verify this idea for him.

Solving the problems of HiSilicon and Huaxin cannot be done in just a few days. While studying and researching, Xu Chuan also devoted some of his energy to other work.

The days passed like this, and in the blink of an eye, the Lantern Festival was here.

In the villa, Tang Sijia knocked on the study door.

After a while, there was movement inside. Xu Chuan came out, glanced curiously at the life assistant in a white coat, and asked, "What's the matter?"

This was the first time he saw the life assistant wearing this kind of doctor's uniform, which looked somewhat similar to the white coat in the laboratory.

Tang Sijia carried two bags and said concisely: "Today is the date of your quarterly physical examination. I will take samples and do a physical examination."

"Oh, okay, wait for me a moment, I'll save the information on the computer." Xu Chuan suddenly understood and nodded.

Since his superiors assigned him a life assistant last year, physical examinations have become the norm for a while.

At first, he would check it every month. Later, he felt that it was too much trouble to do it once every month, and wanted to change it to once a year.

After all, ordinary people usually only have a physical examination once a year. However, Tang Sijia argued with him and finally decided to have a simple physical examination once a quarter and a detailed physical examination once a year.

Counting the time, today is almost the first quarter.

After drawing two samples of blood for physical examination, Tang Sijia saved the samples and then handed over a tool.

"This is for collecting urine, do you need my help?"

Xu Chuan coughed slightly and took the tool: "I can do it myself."

How can others help with this kind of thing?

After taking care of the physical examination, Tang Sijia checked and recorded physical information such as blood pressure, weight, height, vision, hearing, etc. After packing the tools, she handed the other bag she brought to Xu Chuan.

Xu Chuan took it and took a look. It looked like a lunch box inside?

"What's this?"

Tang Sijia smiled and said: "Tangyuan, isn't today the Lantern Festival? I guess you won't remember it, so I asked Aunt Lin to make a reunion dinner and bring it over."

Xu Chuan took out the lunch box and opened it. There were really white and moist glutinous rice balls inside, steaming hot.

Closing the lid, he smiled and said, "Thanks."

Eating glutinous rice balls during the Lantern Festival is also a southern custom, but he hasn't had it for a long time.

After all, by the Lantern Festival, he had basically left his hometown.

When he lives alone, he will not deliberately remember to order glutinous rice balls on this day.

Taking the glutinous rice balls with him, Xu Chuan turned and entered the study.

On the desk, the phone was ringing. It was the president of Nanjing University calling.

"Academician Xu, have a good Lantern Festival." The phone was connected, and Tan Shaoyuan's cheerful voice came from the other end.

Xu Chuan responded with a smile: "Have fun together, and wish Principal Tan good health."

After a few words of greeting, Tan Shaoyuan asked with a smile: "I wonder when Academician Xu plans to return to Jinling."

Xu Chuan: "I have returned to Jinling. What can I do?"

Tan Shaoyuan: "That's right. I called you this time mainly because of the unified framework theory of strongly correlated electron systems that you proved and perfected at the end of last year. The school has received many inquiries from physicists at home and abroad. , they are all asking you when will you explain the opening report."

"So I want to ask you when is convenient so that the school can prepare in advance."

After hearing this, Xu Chuan thought for a moment and said, "In ten days, then. I'm busy with other things for the time being."

These days, he has become familiar with a lot of things related to neural network architecture, and is going to use these ten days to solve the problems of HiSilicon and Huaxin.

Although the time is short, it may not be possible to achieve the optimal solution, but judging from previous exchanges, it seems that the other side is quite anxious about this matter.

In this case, let’s solve the problem first. As for optimization, we can do it later when we have time.

One bite of this kind of thing won't make you a fat man.

Tan Shaoyuan: "No problem, it just depends on your time. The school can do it at any time. Let's just say it. The school will send out the notices and announcements first and be prepared."

Xu Chuan nodded and said with a smile: "Okay, it's just a trouble for the school."

Tan Shaoyuan: "Hey, how can this be said to be trouble? You know, Shuimu Peking University can't even ask for it. So I won't disturb you much today, Academician Xu. Let's talk when we have time."

"OK."

After hanging up the phone, Xu Chuan looked at the phone with a black screen and shook his head with a smile.

Speaking of the unified framework of strongly correlated electronic systems, almost a month has passed from the year before to now. It is estimated that many people in the physics community can't wait. If they can't find him, they can only find it. Southern University.

But so much time has passed, and it’s time to give the outside world a response.

PS: Second update, please give me a monthly pass