I originally planned the mobile as a piece on metacognition, as it apparently is. Then I was about to accompany it with an essay about how we deliberate and reach a decision, which I studied during my PhD.
But while I was making it, I also realized that I had ideas like this, and others, from when I was little. I felt like I’ve only made it now because now I have more experience executing such ideas.
In that sense, the mobile could be also about growth: a larger self looking back on the little selves. Indeed, metacognition, or evaluation of one’s own thinking, can be one way for learning and growth for humans and machines. For example, if you were sure you would be invited to a friend’s birthday and if you were not, you would wonder about the reason and might learn more about what happened to the friend or to your friendship. That’s different from when you were unsure about getting the invitation to begin with, in which case being not invited wouldn’t mean much.ย Therefore, the sense of being sure, or confidence, is a form of metacognition that can help learning. Machines use confidence to learn as well: agreement between the graded sense of confidence and the all-or-none outcomes can beย mathematically expressed as “cross entropy“, which is a standard measureย used in training machines.
Back to the mobile, I debated whether to use wires or paper, but chose paper because each figure is planar. I glued several sheets together to reinforce them. If someone wants it in a more permanent form, I’d like to try 3D printing it.
์๋๋ ๋ฉํ-์ธ์ง์ ๊ดํ ๋ชจ๋น๋ก ๊ณํํ๋ค. ์ง๊ธ๋ ๊ทธ๋ ๊ฒ ๋ณผ ์ ์๋ค. ์ค๋ช ์ผ๋ก๋ ์ฐ๋ฆฌ๊ฐ ์ด๋ป๊ฒ ๊ณ ๋ฏผํ๊ณ ๊ฒฐ๋ก ์ ๋๋ฌํ๋์ง์ ๋ํด, ๋ด๊ฐ ๋ฐ์ฌ๊ณผ์ ๋ ์ฐ๊ตฌํ๋ ๋ด์ฉ์ ๊ณ๋ค์ฌ ์ธ ์๊ฐ์ด์๋ค.
ํ์ง๋ง ๋ชจ๋น์ ๋ง๋๋ ๋์, ์ด๋ฆด ๋๋ ์ด๋ฐ ์์ด๋์ด๋ฅผ ํฌํจํด ์ฌ๋ฌ ์์ด๋์ด๋ค์ด ์์๋ ๊ฒ์ด ๊ธฐ์ต๋ฌ๋ค. ์ด์ ์ผ ์ด ๋ชจ๋น์ ๋ง๋ค๊ฒ ๋ ๊ฒ์, ์ด์ ์์ผ ๊ทธ ์์ด๋์ด๋ฅผ ์คํํ ์ ์๊ฒ ๋์ด์๋ผ๋ ์๊ฐ์ด ๋ค์๋ค.
๊ทธ๋ฐ ์๋ฏธ์์, ์ด ๋ชจ๋น์ ์ฑ์ฅ์ ๊ดํ ์ํ์ผ ์๋ ์๊ฒ ๋ค: ํฐ ์์ ์ด ์์ ์์ ๋ค์ ๋ฐ์ถํ๋ ๊ฒ์ด๋ค. ๋ฉํ-์ธ์ง, ํน์ ์ค์ค๋ก์ ์๊ฐ์ ๋ํ ํ๋จ์ ์ค์ ๋ก ์ฌ๋์ด๋ ๊ธฐ๊ณ๊ฐ ๋ฐฐ์ฐ๊ณ ์ฑ์ฅํ๋ ๋ฐ ๋์์ด ๋๋ค. ์์ปจ๋ ์ด๋ค ์น๊ตฌ์ ์์ผํํฐ์ ์ด๋๋ ๊ฑฐ๋ผ๊ณ ํ์ ํ๋๋ฐ ์ด๋๋ฐ์ง ๋ชปํ๋ค๋ฉด, ๊ทธ ์น๊ตฌ๋ ์น๊ตฌ์์ ์ฐ์ ์ ๋ํด ๋ค์ ์๊ฐํด๋ณด๊ณ ๋ญ๊ฐ๋ฅผ ๋ ๋ฐฐ์ธ ์ ์์ ๊ฒ์ด๋ค. ํ์ง๋ง ์ด๋๋ฐ์์ง ์ฌ๋ถ๊ฐ ์ ์ด์ ๋ถํ์คํ๋ค๋ฉด, ์ด๋๋ฅผ ๋ชป ๋ฐ์๋ ๋ณ ๋ป์ด ์์๋ค๊ณ ์ฌ๊ธธ ๊ฒ์ด๋ค. ์ด๋ ๊ฒ ์์ ๊ฐ์ ๋ฐฐ์์ ๋์ธ ์ ์๋ ๋ฉํ–์ธ์ง์ ํ ํํ์ด๋ค. ์์ ๊ฐ์ ๊ธฐ๊ณ๋ค์ ํ๋ จ์๋ ์ฐ์ธ๋ค:ย ์์ ๊ฐ๊ณผ ์ค์ ๊ฒฐ๊ณผ ์ฌ์ด์ ์ผ์น๋๋ ์ํ์ ์ผ๋ก “ํฌ๋ก์ค ์ํธ๋กํผ“๋ก ํํ๋ ์ ์์ผ๋ฉฐ, ์ด๋ ๊ธฐ๊ณ๋ค์ ํ๋ จํ ๋ ์ผ์์ ์ผ๋ก ์ฐ์ด๋ ์ฒ๋์ด๋ค.
๋ชจ๋น๋ก ๋์์์, ์ฒ ์ฌ๋ฅผ ์ธ์ง ์ข ์ด๋ฅผ ์ธ์ง ๊ณ ๋ฏผํ๋ค๊ฐ, ๊ฐ ์ธ๋ฌผ์ ๋์์ธ์ด ํ๋ฉด์ ์ด๊ธฐ ๋๋ฌธ์ ์ข ์ด๋ฅผ ์ฐ๊ธฐ๋ก ํ๋ค. ์ข ์ด ๋ช ์ฅ์ ํจ๊ป ๋ถ์ฌ์ ๋จ๋จํ๊ฒ ์ธ์ธ ์ ์๋๋ก ๋ง๋ค์๋ค. ๋ ํผํผํ ๋ฒ์ ์ ์ํ๋ ์ฌ๋์ด ์๋ค๋ฉด 3D ํ๋ฆฐํ ์ผ๋ก ๋ง๋ค์ด ๋ณด๊ณ ์ถ๋ค.
YK 2019.