![](https://360ua.news/wp-content/uploads/2023/12/screenshot_8-30-696x434.png "Rewrite the news: It's no secret that the brain is not working as a computer e -chains. They have different architecture, which they dream of more than one generation of scientists. The brain stores and processes data in one place, while the computer constantly forwards them between the processor and memory jars. The main problem in the absence of a corresponding memory cell, which at the same time played the role of a transistor, with which scientists from the United States promise to help. A team of scientists from Northwestern University, Boston College (Boston College) and the Massachusetts Institute of Technology (MIT) reported that they have created and tested the so-called synaptic transistor, which was capable of working in the neuron network. The main advantage of development, scientists consider the ability of the transistor to work at room temperature with extremely small consumption of 20 PVT (pikovatt). In the living nerve tissue, the synapses are the gap between the end of one neuron and the beginning of the other (when it comes to the brain or spinal cord). In this interval, biochemical reactions are responsible for transmitting a nerve impulse further or locking it. The transistor presented by scientists performs a similar function, but in his work he uses physical phenomena and processes. By and large, the technology belongs to the sphere of mowing quantum materials. In many cases, such materials work under the conditions of cryogenic cooling. Therefore, it was important for the researchers' team to show the effect at room temperature, which they successfully coped with. The transistor, if it can be called, is two layers of atomic thickness imposed on each other, slightly displaced relative to each other in the horizontal plane. One layer is graphene, and the other layer is a nitride of the boron with hexagonal lattice. The rotation of one of them to a certain angle creates a moraine pattern of two combined structures, and that is all the miracle. The right angles at which expressive interactions are revealed are even commonly called magical. At certain angles of rotation, the Kulonsky interactions between the two materials go into the category of exotic electrical interactions, which do not occur in ordinary materials, which opens the potential for the use of such structures in future electronics with known functionality. To the honor of the researchers, they went further and created a number of neural chains on the basis of the presented transistor transitions, which showed the ability to associative learning. Experimental schemes learned to recognize groups of numbers in binary coding, which they successfully coped with. For example, neural chains separated the combinations of 000 and 111 from 101, showing the associative connection of the first and their difference from the third combination. Thus, in the annotation in the article in the journal Nature scientists, "Muar synaptic transistor provides effective schemes of calculations in memory and provide advanced hardware accelerators for artificial intelligence and machine training."")
A group of scientists from Northwestern University, Boston College and Massachusetts Institute of Technology has announced the successful creation and testing of a new synaptic transistor who can integrate into neural networks for associative training. This development solves the problem of the absence of a corresponding memory cell in traditional computers that constantly transmit data between the processor and memory banks.
The main advantage of a new transistor is its ability to operate at room temperature with minimal energy consumption, which is only 20 PVT (pikovatt). The researchers used the concept of moraine quantum materials, where one layer consists of graphene and the other - of boron nitride. The location of the layers provides a mora pattern, which is a key element for identifying magical angles where expressive interactions occur.
Scientists went further, creating neural chains based on these transistors who revealed the ability to associative learning. Experiments have shown that neural networks are able to recognize and separate certain combinations in binary coding. This development opens new prospects for effective memory computing schemes and involves the use in advanced hardware accelerators for artificial intelligence and machine learning.
