728x90
๋ฐ˜์‘ํ˜•

๋จธ์‹ ๋Ÿฌ๋‹ 2

[๋ถ€์ŠคํŠธ์บ ํ”„ AI Tech 3๊ธฐ Pre-Course] ์ธ๊ณต์ง€๋Šฅ ๋ณธ๊ฒฉ ํƒ๊ตฌ : Optimization, Gradient Descent, Overfitting, Generalization, Cross-Validation, SGD

๋ชจ๋“  ๊ฒŒ์‹œ๋ฌผ์€ macOS Monterey 12.0.1 ๋ฒ„์ „ ๊ธฐ์ค€์œผ๋กœ ์ž‘์„ฑํ•˜์˜€์Šต๋‹ˆ๋‹ค. ๋ถ€์ŠคํŠธ์บ ํ”„ AI Tech 3๊ธฐ๋ฅผ ์œ„ํ•œ Pre-Course ๋ฅผ ํ† ๋Œ€๋กœ ์ž‘์„ฑํ•˜์˜€์Šต๋‹ˆ๋‹ค. Introduction 1. Generalization Iteration์ด ๋ฐ˜๋ณต๋  ๋•Œ๋งˆ๋‹ค Training Error๋Š” ๋‹น์—ฐํžˆ ์ค„์–ด๋“ค ๊ฒƒ์ด๋‹ค. ํ•˜์ง€๋งŒ ์‹œ๊ฐ„์ด ์ง€๋‚˜๊ฐ€๊ณ  ๋‚˜๋ฉด Test Error์— ๋Œ€ํ•ด ๊ทธ ์„ฑ๋Šฅ์ด ๋–จ์–ด์ง€๊ฒŒ ๋œ๋‹ค. ์ฆ‰, Training Error์™€ Test Error ์‚ฌ์ด์˜ ์ฐจ์ด๊ฐ€ ์ฆ๊ฐ€ํ•œ๋‹ค. ์ด๋Ÿฌํ•œ ํ˜„์ƒ์„ ์˜ค๋ฅธ์ชฝ ์ด๋ฏธ์ง€์™€ ๊ฐ™์ด Overfitting์ด๋ผ ํ•œ๋‹ค. ํ•™์Šต ๋ฐ์ดํ„ฐ์กฐ์ฐจ ๋งž์ถ”์ง€ ๋ชปํ•˜๊ณ  ์žˆ๋Š” ๊ฒƒ์ด Underfitting. 2. Cross-Validation ์ผ๋ฐ˜์ ์œผ๋กœ ํ•™์Šต๊ณผ ํ…Œ์ŠคํŠธ๋ฅผ ์œ„ํ•œ ๋ฐ์ดํ„ฐ๋ฅผ ๋‚˜๋ˆ ์„œ ํ›ˆ๋ จ์‹œํ‚ค๋Š” ๊ฒฝ์šฐ๊ฐ€ ๋งŽ๋‹ค...

[๋ถ€์ŠคํŠธ์บ ํ”„ AI Tech 3๊ธฐ Pre-Course] ์ธ๊ณต์ง€๋Šฅ ๋ณธ๊ฒฉ ํƒ๊ตฌ : ๋”ฅ๋Ÿฌ๋‹ ๊ธฐ์ดˆ ๋‰ด๋Ÿด ๋„คํŠธ์›Œํฌ MLP (Multi-Layer Perceptron)

๋ชจ๋“  ๊ฒŒ์‹œ๋ฌผ์€ macOS Monterey 12.0.1 ๋ฒ„์ „ ๊ธฐ์ค€์œผ๋กœ ์ž‘์„ฑํ•˜์˜€์Šต๋‹ˆ๋‹ค. ๋ถ€์ŠคํŠธ์บ ํ”„ AI Tech 3๊ธฐ๋ฅผ ์œ„ํ•œ Pre-Course ๋ฅผ ํ† ๋Œ€๋กœ ์ž‘์„ฑํ•˜์˜€์Šต๋‹ˆ๋‹ค. Neural Network ์ƒ๋ฌผํ•™์  ๋‡Œ์˜ ์‹ ๊ฒฝ๋ง์„ ๋ชจ๋ฐฉํ•œComputing System. ์ด๋ฏธ์ง€๋ผ๋Š” ํ…์„œ๊ฐ€ ์ฃผ์–ด์ง€๋ฉด ๋ผ๋ฒจ์ด๋ผ๋Š” ๋ฒกํ„ฐ๊ฐ€ ์‚ฐ์ถœ๋˜๋Š” ๋ชจ๋ธ์ด ์žˆ๋‹ค๊ณ  ํ•˜์ž. ๋‚ด๊ฐ€ ์ •์˜ํ•œ ํ•จ์ˆ˜(ํ–‰๋ ฌ ์—ฐ์‚ฐ๊ณผ ๋น„์„ ํ˜• ์—ฐ์‚ฐ์˜ ๋ฐ˜๋ณต)๋กœ ์ด๋ฅผ ๊ทผ์‚ฌํ•˜๊ฒ ๋‹ค. ์ž…๋ ฅ๊ณผ ์ถœ๋ ฅ์ด 1์ฐจ์›์ธ ๋ฌธ์ œ๊ฐ€ ์žˆ๋‹ค๊ณ  ํ•˜์ž. ์„ ํ˜•ํšŒ๊ท€. ๊ทธ ๋ชฉ์ ์€ ์ž…๋ ฅ๊ณผ ์ถœ๋ ฅ์„ ์—ฐ๊ฒฐํ•˜๋Š” ๋ชจ๋ธ์„ ์ฐพ๋Š” ๊ฒƒ์ด๋‹ค. ์„ ํ˜•์ด๋ฏ€๋กœ ๋ผ์ธ์— ๋Œ€ํ•œ ๊ธฐ์šธ๊ธฐ์™€ y์ ˆํŽธ ๋‘ ํŒŒ๋ผ๋ฏธํ„ฐ๋ฅผ ์ฐพ๋Š” ๋ฌธ์ œ๊ฐ€ ๋  ๊ฒƒ์ด๋‹ค. ๋ฐ์ดํ„ฐ๋Š” 1์ฐจ์› x์™€ y๊ฐ€ N๊ฐœ ๋ชจ์—ฌ์žˆ๋‹ค. x์—์„œ y_hat์œผ๋กœ mapping ์‹œํ‚ค๋Š” ์„ ํ˜•๋ชจ๋ธ ๊ทธ ๊ธฐ์šธ๊ธฐ์™€ ์ ˆํŽธ์„ ์ฐพ๋Š”..

728x90
๋ฐ˜์‘ํ˜•