$$\newcommand{\floor}[1]{\left\lfloor #1 \right\rfloor} \newcommand{\ceil}[1]{\left\lceil #1 \right\rceil} \newcommand{\N}{\mathbb{N}} \newcommand{\R}{\mathbb{R}} \newcommand{\Z}{\mathbb{Z}} \newcommand{\Q}{\mathbb{Q}} \newcommand{\C}{\mathbb{C}} \renewcommand{\L}{\mathcal{L}} \newcommand{\x}{\times} \newcommand{\contra}{\scalebox{1.5}{\lightning}} \newcommand{\inner}[2]{\left\langle #1 , #2 \right\rangle} \newcommand{\st}{\text{ such that }} \newcommand{\for}{\text{ for }} \newcommand{\Setcond}[2]{ \left\{\, #1 \mid #2 \, \right\}} \newcommand{\setcond}[2]{\Setcond{#1}{#2}} \newcommand{\seq}[1]{ \left\langle #1 \right\rangle} \newcommand{\Set}[1]{ \left\{ #1 \right\}} \newcommand{\set}[1]{ \set{#1} } \newcommand{\sgn}{\text{sign}} \newcommand{\halfline}{\vspace{0.5em}} \newcommand{\diag}{\text{diag}} \newcommand{\legn}[2]{\left(\frac{#1}{#2}\right)} \newcommand{\ord}{\text{ord}} \newcommand{\di}{\mathrel{|}} \newcommand{\gen}[1] \newcommand{\irr}{\mathrm{irr }} \renewcommand{\deg}{\mathrm{deg }} \newcommand{\nsgeq}{\trianglelefteq} \newcommand{\nsg}{\triangleleft} \newcommand{\argmin}{\mathrm{argmin}} \newcommand{\argmax}{\mathrm{argmax}} \newcommand{\minimize}{\mathrm{minimize}} \newcommand{\maximize}{\mathrm{maximize}} \newcommand{\subto}{\mathrm{subject\ to}} \newcommand{\DKL}[2]{D_{\mathrm{KL}}\left(#1 \di\di #2\right)} \newcommand{\ReLU}{\mathrm{ReLU}} \newcommand{\E}{\mathbb{E}} \newcommand{\expect}[1]{\E\left[#1\right]} \newcommand{\expectwith}[2]{\E_{#1}\left[#2\right]} \renewcommand{\P}{\mathbb{P}} \newcommand{\uniform}[2]{\mathrm{Uniform}\left(#1 \dots #2\right)} \newcommand{\gdist}[2]{\mathcal{N}\left(#1, #2\right)}$$

Total views

# What is This?

์ด ์นดํ๊ณ ๋ฆฌ์ ๊ธ๋ค์ ํฌ๊ฒ ์๋ ์ธ ๊ฐ์ง์ ๊ธฐ๋ฐํ๊ณ  ์์ต๋๋ค.

์ ๊ฐ ์ ๋ฆฌํ ๋ด์ฉ์ ๊ณผ๋ชฉ์ officialํ ๊ฐ์์๋ฃ์ ์๋ฌด๋ฐ ์๊ด์ด ์์ผ๋ฉฐ, ์ ๊ฐ ์ด๋ฏธ ์ ์๊ณ  ์๋ ๋ด์ฉ์ ์คํตํ ๊ฒ๋ ๋ง๊ณ , ๋ค๋ฅธ ์๋ฃ๋ฅผ ์ฐพ์๋ณด๋ฉฐ ์ถ๊ฐํ ๋ด์ฉ๋ ๋ง์ต๋๋ค. ์ฆ, ์ฌ๊ธฐ ์๋ ํฌ์คํ์ ๊ณผ๋ชฉ์์ ์ค์ ๋ก ๊ฐ์๋ ๋ด์ฉ๊ณผ ์ผ์นํ์ง ์์ ์ ์์ต๋๋ค. ํนํ, ์คํ๋ ์ค๋ฅ๊ฐ ์๋ค๋ฉด ๋งค์ฐ ๋์ ํ๋ฅ ๋ก ์ ๊ฐ ์ดํดํ ๊ฒ์ ์ ๋ค๊ฐ ์ค์ํ์๊ฑฐ๋ ์๋ชป ์ดํดํ๊ณ  ์์ ๊ฐ๋ฅ์ฑ์ด ๋์ต๋๋ค.

1. Goodfellow, Bengio, Courville์ ์ ์ Deep Learning ์ ๋ด์ฉ์ ๊ณต๋ถํ๊ณ  ์ ๋ฆฌํ ๋ด์ฉ
2. 2021 ๊ฐ์ํ๊ธฐ์ ์๊ฐํ๋ ์์ ํด์ํํน๊ฐ : ์ฌ์ธตํ์ต์ ์์นํด์ ์์ ๊ณต๋ถํ ๋ด์ฉ (1์ ์ฑ์ ๊ต์ฌ๋ก ์ฌ์ฉํ๋ ์์์๋๋ค)
3. 2021 ๊ฐ์ํ๊ธฐ์ ์๊ฐํ๋ ์์ ์ฌ์ธต ์ ๊ฒฝ๋ง์ ์ํ์  ๊ธฐ์ด ์์ ๊ณต๋ถํ ๋ด์ฉ (2์ ๋นํด ์ํ์ ์ธ ๋ฉด์ ์ง์คํ๋ ์์์๋๋ค)

๊ฐ์์ ์ฑ์ ๋ด์ฉ์ ์ ๊ฐ ์ ๋นํ ์  ๊ณต๋ถํ ๋ฐฉํฅ์ ๋ง๊ฒ ์ฌ๊ตฌ์ฑํ ๋ถ๋ถ๋ค์ด ๋ง์, ์์๊ฐ ํน์  ์๋ฃ๋ฅผ ๋ฐ๋ฅด์ง ์์ต๋๋ค.

์ฌ๋ฐ๊ฒ๋ ์ ๊ฐ ์ด ๋ธ๋ก๊ทธ์ ์ฐ๊ธฐ ์์ํ ๊ธ์ -์ต๋๋ค๋ก, ํ๊ธฐ๋ธํธ๋ฅผ $\LaTeX$๋ก ์ ๋ฆฌํ๊ณ  ๊ทธ๊ฑธ ๋ค์ pandoc์ผ๋ก ๋งํฌ๋ค์ด ๋ณํํ ํฌ์คํ๋ค์ -๋ค๋ก ๋๋ฉ๋๋ค. ์ด๊ฑธ ๋ชจ๋ ์ธ์  ๊ฐ๋ -์ต๋๋ค๋ก ํต์ผํ๊ฒ ๋ค๋ ์๋ํ ๊ฟ์ด ์์ง๋ง ๋น๋ถ๊ฐ์ ์ฝ์ง ์์ ์์ ์๋๋ค.

์ฐธ๊ณ  3๋ฒ ์์์ ๊ฒฝ์ฐ $\LaTeX$ ๋ก ํ๊ธฐ๋ธํธ๋ฅผ ๊ด๋ฆฌํ๊ณ  ์์ต๋๋ค. ์ธ์  ๊ฐ ์ฌ๊ฑด์ด ํ๋ฝํ๋ค๋ฉด ์ด ๋ธํธ๋ฅผ ์ฌ๊ธฐ์ ์ฌ๋ฆดํ๋ฐ, pandoc์ผ๋ก ์ด ํฌ์คํ์ ๊ทธ์ชฝ์ด ์ข๋ ๊น๋ํ๊ฒ ๋ณด์ผ ๊ฒ ๊ฐ์ต๋๋ค. ์ต์ข์ ์ผ๋ก๋ ๋งค์ฐ ์ ๋ชํ Evan Chen Notes ๊ฐ์ ๊ฒฐ๊ณผ๋ฌผ์ ๋ชฉํํ๊ณ  ์๋๋ฐ, ๋ค์ํ ์ด์๋ค์ด ์์ต๋๋ค. ๊ฐ์ฅ ๋จผ์ , ์ด ์๋ฃ๋ฅผ ๊ณต๊ฐํด๋ ๋๋์ง์ ๋ฌธ์ ๊ฐ ์๋๋ฐ, ์๋ณธ ๊ฐ์์๋ฃ๊ฐ ๊ต์๋์ ๊ฐ์ธ ์น์ฌ์ดํธ ์ ์ด๋ค ๋ก๊ทธ์ธ์ด๋ ํ๊ต ๊ณ์  ์๊ตฌ ์์ด ์ฌ๋ผ์ ์์ผ๋ฏ๋ก (์๋ง๋) ๊ด์ฐฎ์ ๊ฒ์ผ๋ก ์๊ฐํ๊ณ  ์์ต๋๋ค. ํนํ ๋งํฌ๋ค์ด ๋ฒ์ ์ ์  edit์ด ์ข ํค๋นํ๊ฒ ๋ค์ด๊ฐ ๊ฑฐ๋ผ์ ์๋ง ํฐ ๋ฌธ์ ๋ ์๋ ๊ฒ์ผ๋ก ์๊ณ  ์๋๋ฐ, $\LaTeX$ scribe note๋ ๊ฐ์ ํ๊ธฐํ ๊ฑฐ๋ผ์ ๊ด์ฐฎ์์ง ์ฌ์ค ์ ๋ชจ๋ฅด๊ฒ ์ต๋๋ค.

# Postings

## Basics / Theory

MLP, CNN ๋ฑ ๋ชจ๋ธ์ ๋ํ ์๊ธฐ๊ฐ ์๋, ์ ์ฒด์ ์ธ ์ด๋ก ์ ๋ํ ์ด์ผ๊ธฐ

## Convolutionary Neural networks

ImageNet Challenge์ ์ญ์ฌ๋ฅผ ๋ฐ๋ผ๊ฐ๋ฉฐ, ๋ช๊ฐ์ง ์ฑ๊ณต์ ์ธ Image classification ๋ชจ๋ธ๋ค์ ๋ํด ๊ณต๋ถํฉ๋๋ค.
CIFAR10์์์ ๊ฒฐ๊ณผ ์ ๋ฆฌ

## Computer Vision

• Semantic Segmentation ๊ฐ์ : Semantic segmentation ๋ฌธ์  ์ ์, ๊ฐ์
• [Fully Convolutional Networks]
• [Encoder-Decoder, U-Net]
• [Dilated Convolutions, DeepLab]