Artificial intelligence and convolutional neural network, convolutional neural network algorithm implementation

What is the principle of artificial intelligence

The principle of artificial intelligence can be simply described as: artificial intelligence = mathematical calculation. The intelligence of a machine depends on the "algorithm". Initially, people discovered that 1 and 0 could be represented by the opening and closing of a circuit.

Then many circuits are organized together, and different arrangements can represent many things, such as colors, shapes, and letters. Coupled with the logic element (transistor), a model of "input (press the switch button) - calculation (current flows through the line) - output (light turns on)" is formed.

Think of a dual control switch in your home. In order to achieve more complex calculations, it eventually became a "large-scale integrated circuit" - a chip. Circuit logic is nested layer by layer and encapsulated layer by layer. Our method of changing the current state becomes "writing a programming language". This is what programmers do.

The computer executes whatever the programmer tells it to do, and the entire process is fixed by the program. Therefore, in order for a computer to perform a certain task, the programmer must first completely understand the flow of the task. Take the jointly controlled elevator as an example: Don’t underestimate this elevator, it is quite “intelligent”.

Consider what judgments it needs to make: up and down direction, whether it is full, peak hours, whether the stop time is sufficient, odd and double floors, etc. You need to think about all possibilities in advance, otherwise bugs will occur. To a certain extent, programmers control the world.

But they always have to do everything by themselves, and the programmers are so tired that their eyes are red from working overtime. So I thought: Can the computer learn by itself and solve problems by itself? And we just need to tell it a set of learning methods.

Everyone still remembers that in 1997, IBM used a specially designed computer to win the chess championship.

In fact, its method is very stupid - brute force calculation, the term is "exhaustive" (in fact, in order to save computing power, IBM manually trimmed a lot of unnecessary calculations for it, such as

Guess you like

Origin blog.csdn.net/aifamao2/article/details/127362603