Interpretable Machine LearningInterpretable Machine Learning A Guide for Making Black Box Models Explainable. Christoph Molnar 2021-05-31 è¦ç´„ 機械å¦ç¿’ã¯ã€è£½å“や処ç†ã€ç ”究を改善ã™ã‚‹ãŸã‚ã®å¤§ããªå¯èƒ½æ€§ã‚’秘ã‚ã¦ã„ã¾ã™ã€‚ ã—ã‹ã—ã€ã‚³ãƒ³ãƒ”ュータã¯é€šå¸¸ã€äºˆæ¸¬ã®èª¬æ˜Žã‚’ã—ã¾ã›ã‚“。ã“ã‚ŒãŒæ©Ÿæ¢°å¦ç¿’を採用ã™ã‚‹éšœå£ã¨ãªã£ã¦ã„ã¾ã™ã€‚ 本書ã¯ã€æ©Ÿæ¢°å¦ç¿’モデルやã€ãã®åˆ¤æ–を解釈å¯èƒ½ãªã‚‚ã®ã«ã™ã‚‹ã“ã¨ã«ã¤ã„ã¦æ›¸ã‹ã‚Œã¦ã„ã¾ã™ã€‚ 解釈å¯èƒ½æ€§ã¨ã¯ä½•ã‹ã‚’説明ã—ãŸå¾Œã€æ±ºå®šæœ¨ã€æ±ºå®šè¦å‰‡ã€ç·šå½¢å›žå¸°ãªã©ã®å˜ç´”ã§è§£é‡ˆå¯èƒ½ãªãƒ¢ãƒ‡ãƒ«ã«ã¤ã„ã¦å¦ã³ã¾ã™ã€‚ ãã®å¾Œã®ç« ã§ã¯ã€ç‰¹å¾´é‡ã®é‡è¦åº¦ (feature importance)ã‚„ALE(accumulated local effects)ã‚„ã€å€‹ã€…ã®äºˆæ¸¬ã‚’説明ã™ã‚‹LIMEやシャープレイ値ã®ã‚ˆã†ãªãƒ¢ãƒ‡ãƒ«ã«éžä¾å˜ãªæ‰‹æ³•(mo
å¤æœ¬ã‚ˆã¿ãŸå±‹ã€€ãŠã˜ã„ã•ã‚“ã®æœ¬ã€è²·ã„ã¾ã™ã€‚ | よã¿ãŸå±‹ã¯æœ¬å¥½ãã®ãŸã‚ã®æ°—軽ãªæœ¬æ ¼å¤æ›¸åº—ã§ã™ã€‚心ç†ãƒ»æ€æƒ³ãƒ»è¶£å‘³ãƒ»ã‚¢ãƒ¼ãƒˆã®å¤æœ¬ãŒå……実ã—ã¦ã„ã¾ã™ã€‚ å°‘ã—手ã«å…¥ã‚Šã«ãã„変ã‚ã£ãŸå¤æœ¬ã‚’ãŸãã•ã‚“ã”用æ„ã—ã¦ãŠå¾…ã¡ã—ã¦ã„ã¾ã™ã€‚å¤ã„本や専門的ãªå¤æœ¬ã®è²·å–ã‚’æ“è¿Žã—ã¾ã™ã€‚ ã”自宅ã¸å‡ºå¼µè²·å–ã«å‚ã‚Šã¾ã™ã€‚é æ–¹ã¸ã¯é‹é€æ¥è€…ã«ã‚ˆã‚‹å¼•ãå–ã‚Šã‚‚è¡Œã„ã¾ã™ã€‚ã”ä¸æ˜Žã®ç‚¹ã¯ã€ŒãŠå•åˆã›ã€ãƒ•ã‚©ãƒ¼ãƒ よりã”連絡ãã ã•ã„。
Philosophy of Science Books in Japanese
Computer Laboratory – Course pages 2014–15: Advanced Functional Programming – Course materials
技術書をèªã‚€èªã‚€è©æ¬º - kuenishi's blog
{{#tags}}- {{label}}
{{/tags}}