activation ์ข…๋ฅ˜
ยท
๐Ÿ‘พ Deep Learning
deserialize(...): Returns activation function given a string identifier. elu(...): Exponential Linear Unit. exponential(...): Exponential activation function. gelu(...): Applies the Gaussian error linear unit (GELU) activation function. get(...): Returns function. hard_sigmoid(...): Hard sigmoid activation function. linear(...): Linear activation function (pass-through). relu(...): Applies the r..
XG ๋ถ€์ŠคํŠธ(eXtream Gradient Boosting)
ยท
๐Ÿ‘พ Deep Learning
์•™์ƒ๋ธ” ๋ชจ๋ธ ์ค‘ ํ•˜๋‚˜์ธ XG ๋ถ€์ŠคํŠธ(eXtream Gradient Boosting)๋Š” ์บ๊ธ€ ์‚ฌ์šฉ์ž์—๊ฒŒ ํฐ ์ธ๊ธฐ๋ฅผ ์–ป๊ณ  ์žˆ๋Š” ๋ชจ๋ธ์ด๋‹ค. *์•™์ƒ๋ธ”: ์—ฌ๋Ÿฌ ๊ฐœ์˜ ํ•™์Šต ์•Œ๊ณ ๋ฆฌ์ฆ˜์„ ์‚ฌ์šฉํ•ด ๋” ์ข‹์€ ์„ฑ๋Šฅ์„ ์–ป๋Š” ๋ฐฉ๋ฒ• ์•™์ƒ๋ธ”์—๋Š” ๋ฐฐ๊น…๊ณผ ๋ถ€์ŠคํŒ…์ด ์žˆ๋‹ค. ensemble ์ข…๋ฅ˜ : single(CNN,RNN) bagging boosting *๋ฐฐ๊น…: ์—ฌ๋Ÿฌ ๊ฐœ์˜ ํ•™์Šต ์•Œ๊ณ ๋ฆฌ์ฆ˜, ๋ชจ๋ธ์„ ํ†ตํ•ด ๊ฐ๊ฐ ๊ฒฐ๊ณผ๋ฅผ ์˜ˆ์ธกํ•˜๊ณ  ๋ชจ๋“  ๊ฒฐ๊ณผ๋ฅผ ๋™๋“ฑํ•˜๊ฒŒ ๋ณด๊ณ  ์ทจํ•ฉํ•ด์„œ ๊ฒฐ๊ณผ๋ฅผ ์–ป๋Š” ๋ฐฉ์‹ *๋ถ€์ŠคํŒ…: ๋ฐฐ๊น…๊ณผ ๋‹ค๋ฅด๊ฒŒ ๋ชจ๋ธ์˜ ๊ฒฐ๊ณผ๋ฅผ ์ˆœ์ฐจ์ ์œผ๋กœ ์ทจํ•ฉ, ๋‹จ์ˆœํžˆ ํ•˜๋‚˜์”ฉ ์ทจํ•ฉํ•˜๋Š” ๋ฐฉ๋ฒ•์ด ์•„๋‹ˆ๋ผ ์ด์ „ ์•Œ๊ณ ๋ฆฌ์ฆ˜, ๋ชจ๋ธ์ด ํ•™์Šต ํ›„ ์ž˜๋ชป ์˜ˆ์ธกํ•œ ๋ถ€๋ถ„์— ๊ฐ€์ค‘์น˜๋ฅผ ์ค˜์„œ ๋‹ค์‹œ ๋ชจ๋ธ๋กœ ๊ฐ€์„œ ํ•™์Šตํ•˜๋Š” ๋ฐฉ์‹ XG ๋ถ€์ŠคํŠธ๋Š” ๋ถ€์ŠคํŒ… ๊ธฐ๋ฒ• ์ค‘ ํŠธ๋ฆฌ๋ถ€์ŠคํŒ…(Tree Boosting) ๊ธฐ๋ฒ•..
๋‹คํ–ˆ๋‹ค
'๐Ÿ‘พ Deep Learning' ์นดํ…Œ๊ณ ๋ฆฌ์˜ ๊ธ€ ๋ชฉ๋ก (9 Page)