º»¹®³»¿ë ¹Ù·Î°¡±â
¹«·á¹è¼Û ¼Òµæ°øÁ¦ Á¤°¡Á¦free

[Book] Machine Learning Design Patterns Solutions to Common Challenges in Data Preparation, Model Building, and Mlops

Paperback
Valliappa Lakshmanan , Robinson, Sara/ Munn, Michael ÁöÀ½ | O'Reilly Media | 2020³â 11¿ù 03ÀÏ

ÀÌ Ã¥ÀÇ ´Ù¸¥ »óǰ Á¤º¸

  • Á¤°¡ : 69,000¿ø
    ÆÇ¸Å°¡ : 66,930¿ø [3%¡é 2,070¿ø ÇÒÀÎ] ÇÒÀÎÄíÆù ¹Þ±â
  • ÇýÅÃ :
    [±âº»Àû¸³] 2010¿ø Àû¸³ [3% Àû¸³] [Ãß°¡Àû¸³] 5¸¸¿ø ÀÌ»ó ±¸¸Å ½Ã 2,000¿ø Ãß°¡Àû¸³ ¾È³» [ȸ¿øÇýÅÃ] ȸ¿ø µî±Þ º°, 3¸¸¿ø ÀÌ»ó ±¸¸Å ½Ã 2~4% Ãß°¡Àû¸³ ¾È³» [¸®ºäÀû¸³] ¸®ºä ÀÛ¼º ½Ã e±³È¯±Ç ÃÖ´ë 300¿ø Ãß°¡Àû¸³ ¾È³»
  • Ãß°¡ÇýÅà : Æ÷ÀÎÆ® ¾È³» µµ¼­¼Òµæ°øÁ¦ ¾È³» Ãß°¡ÇýÅà ´õº¸±â
  • ¹è¼Ûºñ : ¹«·á ¹è¼Ûºñ ¾È³»
  • µµ¼­»óÅ : ÇöÀç´Â µµ¼­ÁÖ¹®ÀÌ ºÒ°¡ÇÕ´Ï´Ù.

¾Ë¸³´Ï´Ù.

  • ¿Ü±¹µµ¼­ÀÇ °æ¿ì ÇØ¿ÜÁ¦°øÁ¤º¸·Î¸¸ ¼­ºñ½ºµÇ¾î ¹ÌÇ¥±âµÈ Á¤º¸°¡ ÀÖÀ» ¼ö ÀÖ½À´Ï´Ù. ÇÊ¿äÇÑ Á¤º¸°¡ ÀÖÀ»°æ¿ì 1:1 ¹®ÀÇ°Ô½ÃÆÇ À» ÀÌ¿ëÇÏ¿© ÁֽʽÿÀ.
»óǰ»ó¼¼Á¤º¸
ISBN 9781098115784(1098115783)
Âʼö 408ÂÊ
¾ð¾î English
Å©±â 178(W) X 233(H) X 21(T) (mm)
Á¦º»ÇüÅ Paperback
ÃѱǼö 1±Ç

Ã¥¼Ò°³

ÀÌ Ã¥ÀÌ ¼ÓÇÑ ºÐ¾ß

The design patterns in this book capture best practices and solutions to recurring problems in machine learning. The authors, three Google engineers, catalog proven methods to help data scientists tackle common problems throughout the ML process. These design patterns codify the experience of hundreds of experts into straightforward, approachable advice.

In this book, you will find detailed explanations of 30 patterns for data and problem representation, operationalization, repeatability, reproducibility, flexibility, explainability, and fairness. Each pattern includes a description of the problem, a variety of potential solutions, and recommendations for choosing the best technique for your situation.

You'll learn how to:

Identify and mitigate common challenges when training, evaluating, and deploying ML models
Represent data for different ML model types, including embeddings, feature crosses, and more
Choose the right model type for specific problems
Build a robust training loop that uses checkpoints, distribution strategy, and hyperparameter tuning
Deploy scalable ML systems that you can retrain and update to reflect new data
Interpret model predictions for stakeholders and ensure models are treating users fairly

¿ø¼­¹ø¿ª¼­ ³»¿ë ¿³º¸±â

µ¥ÀÌÅÍ Áغñ, ¸ðµ¨ ±¸Ãà, MLOpsÀÇ ÀϹÝÀûÀÎ ¹®Á¦¿¡ ´ëÇÑ ¼Ö·ç¼Ç ±¸ÇöÇϱâ

µðÀÚÀÎ ÆÐÅÏÀ̶õ Àü¹®°¡ ¼ö¹é ¸íÀÇ °æÇèÀ» °£´ÜÇϰí Á¢±ÙÇϱ⠽±°Ô ü°èÈ­ÇÑ °ÍÀÌ´Ù. ÀÌ Ã¥¿¡´Â µ¥ÀÌÅÍÀÇ Ç¥Çö, ¿î¿µ, ¹Ýº¹¼º, ÀçÇö¼º, À¯¿¬¼º, ¼³¸í °¡´É¼º, °øÁ¤¼º¿¡ ´ëÇÑ 30°¡Áö µðÀÚÀÎ ÆÐÅÏÀÌ ´ã°Ü ÀÖ´Ù. °¢ ÆÐÅÏ¿¡´Â ¹®Á¦¿¡ ´ëÇÑ ¼³¸í, ´Ù¾çÇÑ ÀáÀçÀû ¼Ö·ç¼Ç, »óȲ¿¡ ÀûÇÕÇÑ ±â¼ú ³ëÇϿ찡 Æ÷ÇԵǾî ÀÖ´Ù. ¸Ó½Å·¯´× ÇÁ·Î¼¼½º Àü¹Ý¿¡ °ÉÃÄ ¸¶ÁÖÇÏ´Â ÀϹÝÀûÀÎ ¹®Á¦¸¦ ÇØ°áÇÏ°í ½ÍÀº ½Ç¹«ÀÚ¶ó¸é, Àú¸íÇÑ 3¸íÀÇ ±¸±Û ¿£Áö´Ï¾î°¡ ÀÌ Ã¥¿¡¼­ ºÐ·ùÇÑ ¡®ÀÌ¹Ì ÀÔÁõµÈ ¹æ¹ý¡¯À» ¹è¿ì°í ½ÇÃµÇØº¸ÀÚ.

ÀÌ Ã¥ÀÇ ¿ø¼­¹ø¿ª¼­

Klover ¸®ºä (0)

ºÏ·Î±× ¸®ºä (0) ¾²·¯°¡±â

ºÏ·Î±× ¸®ºä´Â º»ÀÎ ÀÎÁõ ÈÄ ÀÛ¼º °¡´ÉÇÕ´Ï´Ù.
Ã¥À̳ª ŸÀο¡ ´ëÇØ ±Ù°Å ¾øÀÌ ºñ¹æÀ» Çϰųª ŸÀÎÀÇ ¸í¿¹¸¦ ÈѼÕÇÒ ¼ö ÀÖ´Â ³»¿ëÀº ºñ°ø°³ ó¸® µÉ ¼ö ÀÖ½À´Ï´Ù.
¡Ø ºÏ·Î±× ¸®ºä ¸®¿öµå Á¦°ø 2021. 4. 1 Á¾·á

¹®Àå¼öÁý (0) ¹®Àå¼öÁý ¾²±â ³ªÀÇ µ¶¼­±â·Ï º¸±â
※±¸¸Å ÈÄ ¹®Àå¼öÁý ÀÛ¼º ½Ã, ¸®¿öµå¸¦ Á¦°øÇÕ´Ï´Ù. ¾È³»

±³È¯/¹Ýǰ/ǰÀý¾È³»

¡Ø »óǰ ¼³¸í¿¡ ¹Ýǰ/±³È¯ °ü·ÃÇÑ ¾È³»°¡ ÀÖ´Â °æ¿ì ±× ³»¿ëÀ» ¿ì¼±À¸·Î ÇÕ´Ï´Ù. (¾÷ü »çÁ¤¿¡ µû¶ó ´Þ¶óÁú ¼ö ÀÖ½À´Ï´Ù.)

±³È¯/¹Ýǰ/ǰÀý¾È³»
¹Ýǰ/±³È¯¹æ¹ý ¸¶ÀÌ·ë > ÁÖ¹®°ü¸® > ÁÖ¹®/¹è¼Û³»¿ª > ÁÖ¹®Á¶È¸ > ¹Ýǰ/±³È¯½Åû ,
[1:1»ó´ã>¹Ýǰ/±³È¯/ȯºÒ] ¶Ç´Â °í°´¼¾ÅÍ (1544-1900)

¡Ø ¿ÀǸ¶ÄÏ, ÇØ¿Ü¹è¼ÛÁÖ¹®, ±âÇÁÆ® ÁÖ¹®½Ã [1:1»ó´ã>¹Ýǰ/±³È¯/ȯºÒ]
    ¶Ç´Â °í°´¼¾ÅÍ (1544-1900)
¹Ýǰ/±³È¯°¡´É ±â°£ º¯½É¹ÝǰÀÇ °æ¿ì ¼ö·É ÈÄ 7ÀÏ À̳»,
»óǰÀÇ °áÇÔ ¹× °è¾à³»¿ë°ú ´Ù¸¦ °æ¿ì ¹®Á¦Á¡ ¹ß°ß ÈÄ 30ÀÏ À̳»
¹Ýǰ/±³È¯ºñ¿ë º¯½É ȤÀº ±¸¸ÅÂø¿À·Î ÀÎÇÑ ¹Ýǰ/±³È¯Àº ¹Ý¼Û·á °í°´ ºÎ´ã
¹Ýǰ/±³È¯ ºÒ°¡ »çÀ¯
  • ¼ÒºñÀÚÀÇ Ã¥ÀÓ ÀÖ´Â »çÀ¯·Î »óǰ µîÀÌ ¼Õ½Ç ¶Ç´Â ÈÑ¼ÕµÈ °æ¿ì
    (´ÜÁö È®ÀÎÀ» À§ÇÑ Æ÷Àå ÈѼÕÀº Á¦¿Ü)
  • ¼ÒºñÀÚÀÇ »ç¿ë, Æ÷Àå °³ºÀ¿¡ ÀÇÇØ »óǰ µîÀÇ °¡Ä¡°¡ ÇöÀúÈ÷ °¨¼ÒÇÑ °æ¿ì
    ¿¹) È­Àåǰ, ½Äǰ, °¡ÀüÁ¦Ç°(¾Ç¼¼¼­¸® Æ÷ÇÔ) µî
  • º¹Á¦°¡ °¡´ÉÇÑ »óǰ µîÀÇ Æ÷ÀåÀ» ÈѼÕÇÑ °æ¿ì
    ¿¹) À½¹Ý/DVD/ºñµð¿À, ¼ÒÇÁÆ®¿þ¾î, ¸¸È­Ã¥, ÀâÁö, ¿µ»ó È­º¸Áý
  • ¼ÒºñÀÚÀÇ ¿äû¿¡ µû¶ó °³º°ÀûÀ¸·Î ÁÖ¹® Á¦À۵Ǵ »óǰÀÇ °æ¿ì ((1)ÇØ¿ÜÁÖ¹®µµ¼­)
  • µðÁöÅÐ ÄÁÅÙÃ÷ÀÎ eBook, ¿Àµð¿ÀºÏ µîÀ» 1ȸ ÀÌ»ó ´Ù¿î·Îµå¸¦ ¹Þ¾ÒÀ» °æ¿ì
  • ½Ã°£ÀÇ °æ°ú¿¡ ÀÇÇØ ÀçÆÇ¸Å°¡ °ï¶õÇÑ Á¤µµ·Î °¡Ä¡°¡ ÇöÀúÈ÷ °¨¼ÒÇÑ °æ¿ì
  • ÀüÀÚ»ó°Å·¡ µî¿¡¼­ÀÇ ¼ÒºñÀÚº¸È£¿¡ °üÇÑ ¹ý·üÀÌ Á¤ÇÏ´Â ¼ÒºñÀÚ Ã»¾àöȸ Á¦ÇÑ ³»¿ë¿¡
    ÇØ´çµÇ´Â °æ¿ì
(1) ÇØ¿ÜÁÖ¹®µµ¼­ : ÀÌ¿ëÀÚÀÇ ¿äû¿¡ ÀÇÇÑ °³ÀÎÁÖ¹®»óǰÀ¸·Î ´Ü¼øº¯½É ¹× Âø¿À·Î ÀÎÇÑ Ãë¼Ò/±³È¯/¹Ýǰ ½Ã ¡®ÇØ¿ÜÁÖ¹® ¹Ýǰ/Ãë¼Ò ¼ö¼ö·á¡¯ °í°´ ºÎ´ã (ÇØ¿ÜÁÖ¹® ¹Ýǰ/Ãë¼Ò ¼ö¼ö·á : ¨ç¼­¾çµµ¼­-ÆÇ¸ÅÁ¤°¡ÀÇ 12%, ¨èÀϺ»µµ¼­-ÆÇ¸ÅÁ¤°¡ÀÇ 7%¸¦ Àû¿ë)
»óǰ ǰÀý °ø±Þ»ç(ÃâÆÇ»ç) Àç°í »çÁ¤¿¡ ÀÇÇØ ǰÀý/Áö¿¬µÉ ¼ö ÀÖÀ¸¸ç, ǰÀý ½Ã °ü·Ã »çÇ׿¡ ´ëÇØ¼­´Â
À̸ÞÀϰú ¹®ÀÚ·Î ¾È³»µå¸®°Ú½À´Ï´Ù.
¼ÒºñÀÚ ÇÇÇØº¸»ó
ȯºÒÁö¿¬¿¡ µû¸¥ ¹è»ó
  • »óǰÀÇ ºÒ·®¿¡ ÀÇÇÑ ±³È¯, A/S, ȯºÒ, ǰÁúº¸Áõ ¹× ÇÇÇØº¸»ó µî¿¡ °üÇÑ »çÇ×Àº
    ¼ÒºñÀÚºÐÀïÇØ°á ±âÁØ (°øÁ¤°Å·¡À§¿øÈ¸ °í½Ã)¿¡ ÁØÇÏ¿© 󸮵Ê
  • ´ë±Ý ȯºÒ ¹× ȯºÒÁö¿¬¿¡ µû¸¥ ¹è»ó±Ý Áö±Þ Á¶°Ç, ÀýÂ÷ µîÀº ÀüÀÚ»ó°Å·¡ µî¿¡¼­ÀÇ
    ¼ÒºñÀÚ º¸È£¿¡ °üÇÑ ¹ý·ü¿¡ µû¶ó ó¸®ÇÔ

ÀÌ Ã¥ÀÇ ÇØ¿ÜÁÖ¹®°¡´Éµµ¼­°¡
ÀÖ½À´Ï´Ù.

ÀÌ Ã¥ÀÇ ¿ø¼­/¹ø¿ª¼­

¾È³»

ÀÌ ºÐ¾ßÀÇ º£½ºÆ®

´õº¸±â+
¹Ù·Î°¡±â
  • ¿ìÃø È®ÀåÇü ¹è³Ê 2
  • ¿ìÃø È®ÀåÇü ¹è³Ê 2
ÃÖ±Ù º» »óǰ