loss function
Image Not Showing
Possible Reasons
- The image file may be corrupted
- The server hosting the image is unavailable
- The image path is incorrect
- The image format is not supported
Learn More →
我們舉個簡單的例子:
這一張考卷的正確解答為 A A B C D
小明的答案是 A B B C D
正確率 80% 錯誤率 20%
小美的答案是 B B A D D
正確率 20% 錯誤率 80%
大家都會比誰的正確率比較高,但在這邊我們需要反向思考
誰的錯誤愈比較低
那什麼是 loss function -> 『損失函數』
在神經網路中就是看看我們的神經網路輸出和正確答案差距有多大
所以 loss function 值越小越好
用上面的例子來講就是錯誤率越低越好啦~~
知道概念接下來就是數學問題了~~
Image Not Showing
Possible Reasons
- The image file may be corrupted
- The server hosting the image is unavailable
- The image path is incorrect
- The image format is not supported
Learn More →
Image Not Showing
Possible Reasons
- The image file may be corrupted
- The server hosting the image is unavailable
- The image path is incorrect
- The image format is not supported
Learn More →
Image Not Showing
Possible Reasons
- The image file may be corrupted
- The server hosting the image is unavailable
- The image path is incorrect
- The image format is not supported
Learn More →
Image Not Showing
Possible Reasons
- The image file may be corrupted
- The server hosting the image is unavailable
- The image path is incorrect
- The image format is not supported
Learn More →
當正確答案和學習機給的答案越小所出來的 loss function 越小
在換個白話一點的
就是我們講的錯誤率
所以你考卷錯得越少你的錯誤率不是越低你也會很開心嗎?
同理,loss function 越小我們越喜歡
那前面為甚麼要除以2 還有為什麼有 sigma 我們先跳過
因為 loss function 有很多種 這只是其中之一