Chapter 163: The Prototype of Convolutional Neural Networks
Looking at the radiant Wang Jiancheng, Chen Nian felt more and more that this kid was really not simple.
If when he proposed a series of future weapon concepts before, he just thought he was chasing his dream, then after talking to him today, I am afraid that I will have to change the wording.
It's not chasing dreams, it's dreaming.
It's difficult, but it's not impossible.
"How are you going to do it? Drone warfare is a complex system, especially when it comes to coordinated operations. β
"You don't know anything about the data link system, and the knowledge system is not complete, so it's too difficult to start a loyal wingman program, right?"
Hearing Chen Nian's words, Wang Jiancheng nodded and replied:
"Senior, I also know it's hard, so I didn't plan to make the project too complicated at the beginning."
"What I want to do is a remote control system that responds in a timely manner."
"In general, it is necessary to integrate the control of the UAV into the existing fighter avionics system, and realize the actions of UAV following, accompaniment, attack, and cover through simple control."
"When the technology is more developed in the future, we will use this as the foundation to implant various tactical templates to achieve one-click control."
"For example, when our satellite and data link systems evolve to be sensitive and powerful enough, we can even configure a J-22 with several UAVs, including electronic jammers, small early warning aircraft, ground attack aircraft, and shield aircraft."
"Awesome."
Chen Nian sighed sincerely.
This set of ideas, what is awesome is not the idea of drone tactics proposed by him, but a sentence:
System integration.
He probably thought he was doing something simple, but in reality, he was really digging the foundation!
If this integrated control system can run smoothly and carry out open iterative development, maybe the first generation of "loyal wingmen" of the republic will really be born in his hands.
"Got an idea?"
Chen Nian continued to ask.
"There it is!"
Wang Jiancheng smiled, pushed away the plate that had been eaten almost completely, and replied:
"My plan is this, this system is easy to say, but it's actually quite large."
"So, I don't have to do it all at once, so I just need to make a simple imitation of the follow-up part first."
"The implementation method is also very simple, directly through data synchronization, but the problem now is that there are differences between the drone and the host in terms of performance, speed, and flight envelope, and it is not very easy to level this gap through algorithms."
"You still know how to code?"
Chen Nian asked in surprise.
"Yes, my dad bought me a computer when I was very young, and he sold the orchard to buy it. I didn't have anything else to do, so I taught myself how to code."
"What language?"
βC#οΌpythonγβ
"Awesome."
In just a few minutes, Wang Jiancheng made Chen Nian sigh several times.
However, when you think about it, it is his father who is even more awesome.
Wang Jiancheng's family conditions are not good, there is an older sister at home, and the economic pressure is not small, in this case, he dares to make such a big gamble on educational resources, which shows that he is definitely not short-sighted.
This can be regarded as a tiger father without a dog to a certain extent.
"What algorithm are you going to use to solve it?"
"Well, what I'm thinking about at the moment is machine learning, giving the wingman some decision-making power, as a complement to imitation. Mainly use ensemble learning, specifically the random forest algorithm, but I feel that this algorithm is still a bit weak. β
"At the moment, there are no more good ideas, let's take one step at a time, I think even so, it is enough to enter the special class."
That's definitely enough.
Even if it's not enough, I'll let Chen Guo arrange it for you.
Chen Nian thought secretly in his heart.
However, the random forest algorithm does seem to be a little behind in this era.
In my memory, it will probably be next year, that is, in 2006, deep learning algorithms will appear.
Instead of asking him to do random forests, why not go directly to deep learning?
This kind of algorithm is not only better in machine learning, but it can even be said that the emergence of deep learning algorithms has triggered a frenzy of explosive growth of AI.
If Wang Jiancheng really gets it out, the future is immeasurable.
Even if it's just a start, laying a foundation for future generations, it's a good attempt.
Thinking of this, Chen Nian opened his mouth and said:
"I have an idea, you can give it a try."
"There should already be some machine learning training models on layer-by-layer initialization on the paper library, and there is more potential to be tapped based on this model."
"With your ability, it shouldn't be too difficult to use ensemble learning at this age and continue to explore deeply."
"You can first look at the most advanced experience in the world and try to use it in your own practice."
"Among them, you can focus on the SVM method, and if you have difficulties, you can ask a statistics teacher for help."
Speaking of this, Chen Nian paused.
It suddenly occurred to him that at this point in time, it should be difficult for the other party to find more useful materials.
But if you let yourself go and parse this part of the content to him.
Rub, 6.9 source points consumed.
Let's pull it down.
So, after carefully recalling for a moment, he continued:
"There are a few keywords that should be used in your research."
"Kernel function expansion, linear regression function, recursion forget it, I'll draw a rough schematic diagram for you."
Chen Nian picked up the chopsticks, dipped the soup on the table and began to write and draw.
He drew the basic structure of the convolutional neural network that was most commonly used in the deep training of game AI.
In fact, the principle of the entire convolutional neural network is not complicated, and the most basic part, even ordinary people with no programming foundation at all, can understand it in half a day.
The real difficulty is how to implement it with complex programs.
This is not what Chen Nian is good at, in the previous life, he just learned it out of interest.
"Well, this is the filtering process diagram of the convolutional neural network, which is the C1 layer, which is used to generate a feature map, and then the features are summed and weighted."
The soup gradually formed a criss-crossing picture on the table, and Wang Jiancheng had been listening wholeheartedly from the very beginning, so even if Chen Nian only spoke once, he had already memorized the whole content in his heart.
When Chen Nian put down his chopsticks, his eyes when he looked at Chen Nian had completely changed.
I thought that this was just an ordinary, more enthusiastic, and a little bit of a senior.
But now it seems.
What a monster this is!
said that he didn't know how to program, and the backhand was an algorithm that was obviously more awesome than a random forest.
Although it is true that this algorithm is not up to the level of immediate use, his thinking is definitely top-notch!
You still say you don't know martial arts!?
Wang Jiancheng carefully wiped off the excess part of the picture with a tissue, and didn't know what to say for a while.
The students passing by looked at this scene curiously, with a funny look on their faces.
He probably thought that these two people were crazy about learning, and their reasoning was pushed to the table.
But what he didn't know was that this picture on the dinner table might become a popular story many years later
After bidding farewell to Wang Jiancheng, Chen Nian wandered back to his residence.
In fact, revealing the information about convolutional neural networks to him is not too advanced a technical leak, because the basic principles of convolutional neural networks were born as early as 2002.
By the time of the 2006 explosion, much of the work of scholars in this process was actually just supplementing and refining the basic principles.
What he did just now was to convey what he already had to Wang Jiancheng, and as for how to really apply it, he still needs to explore.
If you really want to say it, such an action is actually equivalent to planting a seed.
According to Wang Jiancheng's talent, even if this seed is not planted by himself, it will be planted by others and other things in a certain study or a certain seminar.
So, on the whole, the risk is very small, but the return is very large.
But
Why didn't the system respond?
Wang Jiancheng, Wang Jiancheng, can you kid do it?
Everyone else is me who broke through as soon as I mentioned it, you still have to digest it, right?
I hope you don't disappoint me, and it would be better if you could surprise me again
Back at his residence, Chen Nian slowly opened his textbook, ready to continue learning his advanced engineering materials.
The progress of this course has reached nearly 70%, and it is expected that in another month, the entire course can be completed, and when the time comes, you can start to try to transfer to the rhythm of scientific research + learning at the same time.
With the blessing of the system, his research on new materials will definitely be much easier than others, and the source point provided by the knowledge increment in the process can also make up for its own consumption.
Virtuous circle!
Chen Nian nodded with satisfaction, turned around and threw himself into studying.
And at this moment, on the other side of the sea, inside the office of the May Society.
Paine sat decadently on the couch, his eyes full of dejection, as if he had lost all light.
He couldn't figure out how this plan could fail again.
The two generals who were personally sent out used the most covert and prudent strategy, but in the end, even they themselves were trapped.
Bond and Sean are all arrested!
What kind of keen perception can be able to locate the initiator after the incident and before the danger is perceived, and even arrange everything to arrest people?
In all fairness, even on your own side, you can't do this kind of efficiency and accuracy.
And across from him, Houston had the same expression.
He looked at the report in his hand, sighed, and said:
"The failure of this operation has had a great impact on us."
"The list we were forced to exchange would be a major blow to our intelligence system over there."
"As things stand, it will take at least four or five years for us to regain the efficiency of our previous intelligence operations."
"Moreover, it is not so easy to deploy new personnel to that side now, especially for the arrangement of the other party's project, which has basically become impossible."
Hearing this, Paine's face became more and more gloomy, but this was far from the end.
"What's more, after this failure, combined with the impact of previous events, Congress's trust in us has been greatly reduced, and if there is no more results, it is likely that our budget will be severely cut the next year."
After saying that, Houston put down the document in his hand without saying a word.
Actually, he had worse news, but in front of Paine, he couldn't say it.
Congress's resentment was not only against the May Society as a group, but more so against Paine himself.
His situation is very dangerous, and some people even ask whether he will be a spy who has been lurking for a long time like Jin Wuxi.
If you weren't a spy, how could you make so many stupid mistakes in a row?
Thankfully, such an opinion is not supported by most people, as they are clear:
If it's really a spy, it won't be so stupid
The two were silent for a moment, and Paine asked:
"We're just losing the final solution, right? What about other routine actions? β
No effect. We did cause a storm of public opinion, but in reality, their decision-makers didn't seem to care. β
"The project is still progressing, and the people who have returned to China have basically arrived in Chengdu, and even recently, their material usage has shown signs of accelerating."
"At this point, we do underestimate them."
Paine let out a long sigh and continued:
"What about other projects? Gas turbine? High-speed rail? β
"In the high-speed rail part, we didn't have the opportunity to intervene, plus they have mastered their own core technology, and the matter is basically a foregone conclusion."
"Alstom and Kawasaki Heavy Industries cooperated with their CRRC and CNR respectively, and Bombardier cooperated with CSR."
"They're unstoppable."
Houston carefully observed Paine's expression, and then said:
"As for the gas turbine project. The layout of our Madasich plant is quite smooth. β
"The model is already in hand, but"
"But what?"
Paine asked, frowning.
"However, after this period of verification, the model fed back by the NAS side is likely to be wrong."
"Maybe it's a trap in itself."
Hearing this, Paine stood up abruptly, he stared at Houston, and asked word for word:
"Any other bad news?"
Houston quickly shook his head and replied:
"Not yet."
Paine breathed a sigh of relief, and secretly rejoiced in his heart:
Fortunately, although the situation is serious, it is not yet out of control.
He looked at Houston and said in a deep voice:
"The problem with the model is not too big, it is not necessarily a trap, it may be that they themselves have a flaw in the design, and with a little time, we can fix it."
"In addition, we can still reclaim the equity of the Madasic plant and thus avoid further losses."
"I'm afraid not."
Houston said in a bitter tone.
"Why?!"
"They started the poison pill program, and now, the business situation of the entire Madasic plant has fallen to a historical low."
"It is already heavily indebted, and most of the equity has fallen into the hands of the Dongqi Group. Even if we take it back now, we will only get a debt. β
Paine was stunned and froze in place, and at this moment, a strange thought even arose in his heart:
In order to get the technology and equipment there, in order to fight for a chance to tear down the barriers, they are willing to do this
Such courage to lose to them, it seems. Also taken for granted?
He felt like his legs were a little weak.
Intense vertigo rushed over his brain, and a moment later, he was completely unconscious in this dark, hidden, yet high office in the sky
(End of chapter)