Euisuk's Dev Log

ใ€Œ์„œ์ฟ  ๊ฐœ๋ฐœ๋…ธํŠธโญใ€

[๋จธ์‹ ๋Ÿฌ๋‹] ์ด์ƒ ํƒ์ง€ ๊ฐœ์š” ๋ฐ ๋ฐ€๋„ ๊ธฐ๋ฐ˜ ์ด์ƒ์น˜ํƒ์ง€

[๋จธ์‹ ๋Ÿฌ๋‹] ์ด์ƒ ํƒ์ง€ ๊ฐœ์š” ๋ฐ ๋ฐ€๋„ ๊ธฐ๋ฐ˜ ์ด์ƒ์น˜ํƒ์ง€ ๋ณธ ํฌ์ŠคํŠธ๋Š” ๊ณ ๋ ค๋Œ€ํ•™๊ต ๊ฐ•ํ•„์„ฑ ๊ต์ˆ˜๋‹˜์˜ ๊ฐ•์˜๋ฅผ ์ˆ˜๊ฐ• ํ›„ ์ •๋ฆฌ๋ฅผ ํ•œ ๊ฒƒ์ž…๋‹ˆ๋‹ค. ์ž‘์„ฑ ๋ฐ ์„ค๋ช…์˜ ํŽธ์˜๋ฅผ ์œ„ํ•ด ์•„๋ž˜ ํฌ์ŠคํŠธ๋Š” ๋ฐ˜๋ง๋กœ ์ž‘์„ฑํ•œ ์  ์–‘ํ•ด๋ถ€ํƒ๋“œ๋ฆฝ๋‹ˆ๋‹ค. Abnormal Data๋ž€ Anomaly Data๋Š” ๋‹ค์Œ๊ณผ ๊ฐ™์ด Hawkins์™€ Harmeling์— ์˜ํ•ด ์ •์˜๋œ๋‹ค. Obse...

[๋จธ์‹ ๋Ÿฌ๋‹] ๊ฑฐ๋ฆฌโ€ข๊ตฐ์ง‘โ€ข์„œํฌํŠธ๋ฒกํ„ฐ ๊ธฐ๋ฐ˜ ์ด์ƒํƒ์ง€ ๊ธฐ๋ฒ•

[๋จธ์‹ ๋Ÿฌ๋‹] ๊ฑฐ๋ฆฌโ€ข๊ตฐ์ง‘โ€ข์„œํฌํŠธ๋ฒกํ„ฐ ๊ธฐ๋ฐ˜ ์ด์ƒํƒ์ง€ ๊ธฐ๋ฒ• ๋ณธ ํฌ์ŠคํŠธ๋Š” ๊ณ ๋ ค๋Œ€ํ•™๊ต ๊ฐ•ํ•„์„ฑ ๊ต์ˆ˜๋‹˜์˜ ๊ฐ•์˜๋ฅผ ์ˆ˜๊ฐ• ํ›„ ์ •๋ฆฌ๋ฅผ ํ•œ ๊ฒƒ์ž…๋‹ˆ๋‹ค. ์ž‘์„ฑ ๋ฐ ์„ค๋ช…์˜ ํŽธ์˜๋ฅผ ์œ„ํ•ด ์•„๋ž˜ ํฌ์ŠคํŠธ๋Š” ๋ฐ˜๋ง๋กœ ์ž‘์„ฑํ•œ ์  ์–‘ํ•ด๋ถ€ํƒ๋“œ๋ฆฝ๋‹ˆ๋‹ค. ๊ฑฐ๋ฆฌ ๊ธฐ๋ฐ˜ ์ด์ƒ์น˜ํƒ์ง€ K-Nearest Neighbor-based Anomaly Detection ๊ฐ ๋ฐ์ดํ„ฐ์— ๋Œ€ํ•œ Anomaly ...

[Paper Review] An Image Is Worth 16x16 Words : Transformers for Image Recognition at Scale (Vision Transformer)

[Paper Review] An Image Is Worth 16x16 Words : Transformers for Image Recognition at Scale (Vision Transformer) ์„ ์ • ์ด์œ  ์•ˆ๋…•ํ•˜์„ธ์š”! ์˜ค๋Š˜ ๋…ผ๋ฌธ๋ฆฌ๋ทฐ, ์ฝ”๋“œ๋ฆฌ๋ทฐํ•ด๋ณผ ๋…ผ๋ฌธ์€ โ€œAn Image Is Worth 16x16 Words: Transformers for I...

[Paper Review] An Architecture Combining Convolutional Neural Network(CNN) and Support Vector Machine(SVM) for Image Classification

[Paper Review] An Architecture Combining Convolutional Neural Network(CNN) and Support Vector Machine(SVM) for Image Classification ์˜ค๋Š˜ ๋ฆฌ๋ทฐ/๋ฒˆ์—ญ/๊ตฌํ˜„ํ•  ๋…ผ๋ฌธ์€ โ€œAbien Fred M. Agarapโ€ ์ €์ž๊ฐ€ ์“ด ๋…ผ๋ฌธ์œผ๋กœ, โ€œYichuan Tan...

[์•Œ๊ณ ๋ฆฌ์ฆ˜] ๊ทธ๋ž˜ํ”„

[์•Œ๊ณ ๋ฆฌ์ฆ˜] ๊ทธ๋ž˜ํ”„ ์˜ค๋Š˜์€ ์•Œ๊ณ ๋ฆฌ์ฆ˜/์ž๋ฃŒ๊ตฌ์กฐ๋ฅผ ๊ณต๋ถ€ํ•˜๋ฉด์„œ ํ‰์†Œ ๋‘๋ ค์›€์— ๋–จ๋ฉฐ ์ œ๋Œ€๋กœ ๊ณต๋ถ€ํ•˜์ง€ ๋ชปํ–ˆ๋˜ ๊ทธ๋ž˜ํ”„์— ๋Œ€ํ•ด ๊ณต๋ถ€๋ฅผ ํ•˜๋ฉฐ ์ •๋ฆฌํ•ด๋ณด์•˜์Šต๋‹ˆ๋‹ค. ๊ณต๋ถ€ํ•˜๋ฉฐ ์ž‘์„ฑํ•œ ๊ธ€์ด๋ฏ€๋กœ ๋ฐ˜๋ง์ด์–ด๋„ ์–‘ํ•ด๋ถ€ํƒ๋“œ๋ฆฝ๋‹ˆ๋‹ค. ๊ทธ๋ž˜ํ”„ ๊ทธ๋ž˜ํ”„๋ž€? ๊ทธ๋ž˜ํ”„๋Š” ๊ฐ€์žฅ ์ผ๋ฐ˜ํ™”๋œ ์ž๋ฃŒ๊ตฌ์กฐ๋กœ, ์—ฐ๊ฒฐ๋œ ๊ฐ์ฒด๋“ค ์‚ฌ์ด์˜ ๊ด€๊ณ„๋ฅผ ์ž˜ ํ‘œํ˜„ํ•จ. ๊ทธ๋ž˜ํ”„ ์ด๋ก  ์ผ...

[๋จธ์‹ ๋Ÿฌ๋‹][์‹œ๊ณ„์—ด] AR, MA, ARMA, ARIMA์˜ ๋ชจ๋“  ๊ฒƒ - ์‹ค์ŠตํŽธ

[๋จธ์‹ ๋Ÿฌ๋‹][์‹œ๊ณ„์—ด] AR, MA, ARMA, ARIMA์˜ ๋ชจ๋“  ๊ฒƒ - ์‹ค์ŠตํŽธ ๋ณธ ํฌ์ŠคํŒ…์€ ์‹ค์ œ ๋ฐ์ดํ„ฐ๋ฅผ ํ™œ์šฉํ•œ ์‹œ๊ณ„์—ด ๋ถ„์„์˜ ์ „๋ฐ˜์ ์ธ ํ”„๋กœ์„ธ์Šค ๊ณผ์ •์„ ๋‹ด๊ณ  ์žˆ์Šต๋‹ˆ๋‹ค. ๋ถ„์„ ํŒ์ด๋‚˜ ํ”ผ๋“œ๋ฐฑ์€ ์–ธ์ œ๋‚˜ ํ™˜์˜์ž…๋‹ˆ๋‹ค!! ๐Ÿ™‡โ€โ™‚๏ธ ๋ถ„์„์˜ ์ˆœ์„œ๋Š” ์•„๋ž˜์™€ ๊ฐ™์Šต๋‹ˆ๋‹ค. ํ•ด๋‹น ๋ถ„์„์€ ์•ž์—์„œ ๋‹ค๋ฃฌ ์‹œ๊ณ„์—ด ๊ฐœ๋…์„ ๊ธฐ๋ฐ˜์œผ๋กœ ๋ถ„์„์„ ์ˆ˜ํ–‰ํ•œ ๊ฒƒ์ด๋ฏ€๋กœ ๊ฐœ๋…์„ ์ฐพ์•„๋ณด๊ณ  ์‹ถ๋‹ค๋ฉด ์ œ...

[๋จธ์‹ ๋Ÿฌ๋‹][์‹œ๊ณ„์—ด] AR, MA, ARMA, ARIMA์˜ ๋ชจ๋“  ๊ฒƒ - ๊ฐœ๋…ํŽธ

[๋จธ์‹ ๋Ÿฌ๋‹][์‹œ๊ณ„์—ด] AR, MA, ARMA, ARIMA์˜ ๋ชจ๋“  ๊ฒƒ - ๊ฐœ๋…ํŽธ ์˜ค๋Š˜์€ ๋จธ์‹ ๋Ÿฌ๋‹ ์‹œ๊ณ„์—ด์—์„œ ๊ฐ€์žฅ ๋งŽ์ด ์“ฐ์ด๋Š” AR, MA, ARMA, ARIMA์— ๋Œ€ํ•ด ์ •๋ฆฌํ•ด๋ณด๋Š” ์‹œ๊ฐ„์„ ๊ฐ€์ง€๋ ค๊ณ  ํ•ฉ๋‹ˆ๋‹ค. ํ•ด๋‹น ํฌ์ŠคํŠธ๋Š” ๊ณ ๋ ค๋Œ€ํ•™๊ต ๊น€์„ฑ๋ฒ” ๊ต์ˆ˜๋‹˜์˜ ๊ฐ•์˜๋ฅผ ๋ฐ”ํƒ•์œผ๋กœ ์ œ์ž‘๋˜์—ˆ์Šต๋‹ˆ๋‹ค. ๋ชฉ์ฐจ ์ •์ƒ ํ”„๋กœ์„ธ์Šค์™€ ๋น„์ •์ƒ ํ”„๋กœ์„ธ์Šค Autoregressive...

[๋จธ์‹ ๋Ÿฌ๋‹][์ฐจ์›์ถ•์†Œ] ๋ณ€์ˆ˜ ์ถ”์ถœ๋ฒ• - Principal Component Analysis (PCA)

[๋จธ์‹ ๋Ÿฌ๋‹][์ฐจ์›์ถ•์†Œ] ๋ณ€์ˆ˜ ์ถ”์ถœ๋ฒ• - Principal Component Analysis (PCA) ๋ณธ ํฌ์ŠคํŠธ๋Š” ๊ณ ๋ ค๋Œ€ํ•™๊ต ๊ฐ•ํ•„์„ฑ ๊ต์ˆ˜๋‹˜์˜ ๊ฐ•์˜๋ฅผ ์ˆ˜๊ฐ• ํ›„ ์ •๋ฆฌ๋ฅผ ํ•œ ๊ฒƒ์ž…๋‹ˆ๋‹ค. ์ž‘์„ฑ ๋ฐ ์„ค๋ช…์˜ ํŽธ์˜๋ฅผ ์œ„ํ•ด ์•„๋ž˜๋Š” ํŽธํ•˜๊ฒŒ ์ž‘์„ฑํ•œ ์  ์–‘ํ•ด๋ถ€ํƒ๋“œ๋ฆฝ๋‹ˆ๋‹ค. Dimensionality Reduction Supervised Variable Extracti...

[๋จธ์‹ ๋Ÿฌ๋‹][์ฐจ์›์ถ•์†Œ] ๋ณ€์ˆ˜ ์„ ํƒ๋ฒ•

[๋จธ์‹ ๋Ÿฌ๋‹][์ฐจ์›์ถ•์†Œ] ๋ณ€์ˆ˜ ์„ ํƒ๋ฒ• ๋ณธ ํฌ์ŠคํŠธ๋Š” ๊ณ ๋ ค๋Œ€ํ•™๊ต ๊ฐ•ํ•„์„ฑ ๊ต์ˆ˜๋‹˜์˜ ๊ฐ•์˜๋ฅผ ์ˆ˜๊ฐ• ํ›„ ์ •๋ฆฌ๋ฅผ ํ•œ ๊ฒƒ์ž…๋‹ˆ๋‹ค. ์ž‘์„ฑ ๋ฐ ์„ค๋ช…์˜ ํŽธ์˜๋ฅผ ์œ„ํ•ด ์•„๋ž˜ ํฌ์ŠคํŠธ๋Š” ๋ฐ˜๋ง๋กœ ์ž‘์„ฑํ•œ ์  ์–‘ํ•ด๋ถ€ํƒ๋“œ๋ฆฝ๋‹ˆ๋‹ค. Dimensionality Reduction Curse of dimensionality ์ •์˜ ์ด๋ก ์ (theory)์œผ๋กœ๋Š” ๋ณ€์ˆ˜์˜ ๊ฐœ์ˆ˜๊ฐ€ ์ฆ๊ฐ€ํ•  ๋•Œ ...

[ํŒŒ์ดํ† ์น˜] ํŒŒ์ดํ† ์น˜ ๊ธฐ์ดˆ ์š”์†Œ (Autograd๋ž€)

[ํŒŒ์ดํ† ์น˜] ํŒŒ์ดํ† ์น˜ ๊ธฐ์ดˆ ์š”์†Œ (Autograd๋ž€) ์ˆœ์ „ํŒŒ์™€ ์—ญ์ „ํŒŒ ์‹ ๊ฒฝ๋ง(Neural Network)์€ ์–ด๋–ค ์ž…๋ ฅ ๋ฐ์ดํ„ฐ์— ๋Œ€ํ•ด ์‹คํ–‰๋˜๋Š” ์ค‘์ฒฉ๋œ ํ•จ์ˆ˜๋“ค์˜ ์ง‘ํ•ฉ์ฒด์ž…๋‹ˆ๋‹ค. ์‹ ๊ฒฝ๋ง์„ ์•„๋ž˜ 2๋‹จ๊ณ„๋ฅผ ๊ฑฐ์ณ ํ•™์Šต๋ฉ๋‹ˆ๋‹ค : ์ˆœ์ „ํŒŒ(Forward Propagation) ์—ญ์ „ํŒŒ(Backward Propagation) Forward Propag...