[📪정보] 딥러닝 창시자, 딥러닝 뛰어넘을 새 AI 구상 밝혀

[익명(211.108)]

https://whowillcare.net/2021/04/16/geoffrey-hinton-has-a-hunch-about-whats-next-for-ai/

딥러닝 창시자 제프리 힌튼이 아직 만들지는 못하고

구상만 한 GLOM이라는 인공지능인데 뭉친다는 뜻의 agglomerate 에서 나옴

- 목표와 특징, 장점

딥러닝은 전체와 부분 중 일부만 알아봤고 보는 각도가 바뀌면 잘 못알아봤는데 이걸 해결 가능

사람처럼 부분을 보고 전체를 그 관계 속에서 알아볼 수 있음

GLOM addresses two of the most difficult problems for visual perception systems: understanding a whole scene in terms of objects and their natural parts; and recognizing objects when seen from a new viewpoint.(GLOM’s focus is on vision, but Hinton expects the idea could be applied to language as well.)

Both of these factors—the part-whole relationship and the viewpoint—are, from Hinton’s perspective, crucial to how humans do vision. “If GLOM ever works,” he says, “it’s going to do perception in a way that’s much more human-like than current neural nets.”

With visual perception, one strategy is to parse parts of an object—such as different facial features—and thereby understand the whole. If you see a certain nose, you might recognize it as part of Hinton’s face; it’s a part-whole hierarchy. To build a better vision system, Hinton says, “I have a strong intuition that we need to use part-whole hierarchies.” Human brains understand this part-whole composition by creating what’s called a “parse tree”—a branching diagram demonstrating the hierarchical relationship between the whole, its parts and subparts. The face itself is at the top of the tree, and the component eyes, nose, ears, and mouth form the branches below.

- 구체적 알고리즘

이미지가 하나 있으면 5겹 정도의 레이어를 씌워서

각각의 레이어내 타일이 여기는 코야! 여기는 눈이야! 주장하고

인접 타일도 그렇게 주장하면 그 주장을 묶어서 더 강하게 받아들이며

그렇게 판단한 눈이나 코 등을 이용해 각도와 사람이름 등을 판단함

A generalized way of thinking about the GLOM architecture is as follows: The image of interest (say, a photograph of Hinton’s face) is divided into a grid. Each region of the grid is a “location” on the image—one location might contain the iris of an eye, while another might contain the tip of his nose. For each location in the net there are about five layers, or levels. And level by level, the system makes a prediction, with a vector representing the content or information. At a level near the bottom, the vector representing the tip-of-the-nose location might predict: “I’m part of a nose!” And at the next level up, in building a more coherent representation of what it’s seeing, the vector might predict: “I’m part of a face at side-angle view!”

But then the question is, do neighboring vectors at the same level agree? When in agreement, vectors point in the same direction, toward the same conclusion: “Yes, we both belong to the same nose.” Or further up the parse tree. “Yes, we both belong to the same face.”

Seeking consensus about the nature of an object—about what precisely the object is, ultimately—GLOM’s vectors iteratively, location-by-location and layer-upon-layer, average with neighbouring vectors beside, as well as predicted vectors from levels above and below.

However, the net doesn’t “willy-nilly average” with just anything nearby, says Hinton. It averages selectively, with neighboring predictions that display similarities. “This is kind of well-known in America, this is called an echo chamber,” he says. “What you do is you only accept opinions from people who already agree with you; and then what happens is that you get an echo chamber where a whole bunch of people have exactly the same opinion. GLOM actually uses that in a constructive way.” The analogous phenomenon in Hinton’s system is those “islands of agreement.”

또다른 인공지능 초네임드 요슈아 벤지오

"힌튼의 직관은 매우 뛰어나며 자주 옳은 것으로 증명되었다.

GLOM에 관심을 가질만한 충분한 이유가 있다"

[ㅂㅈㅁㄴ(hh89724)]

[ㅁㄴㅇㄹ(210.97)]

온다.... - dc App

[ㅇ(221.158)]

근데 아무리 뛰어난 학자도 70대에 획기적인 성과를 내는 경우는 거의 없지 않나... 실험분야는 그나마 가능성 있는데 이론쪽은 50만 넘어도 은퇴각인데

[익명(211.47)]

촘스키는 90이 넘어도 통사분야에서 현역임 심리학도 그렇고 대체로 학제적으로 봤을 때 인지학문에 속하는 분과들이 학자들이 장수하거나 오래도록 학계에 기여하는 경향이 기묘한 경향이 있음

[익명(163.152)]

드물게 예외는 있지 뭐 블랙홀 존재를 최초로 이론족으로 증명한 찬드라셰카르도 그렇고

[익명(121.148)]

cnn에 knn을 복합한 알고리즘인가.. 새로운 알고리즘이라고 하기에는