π ΠΠ΄Π΅ΠΈ ΠΌΠ°ΡΠΈΠ½Π½ΠΎΠ³ΠΎ ΠΎΠ±ΡΡΠ΅Π½ΠΈΡ: ΠΎΡ ΡΠ΅ΠΎΡΠΈΠΈ ΠΊ Π°Π»Π³ΠΎΡΠΈΡΠΌΠ°ΠΌ [2019] Π¨Π°ΠΉ Π¨Π°Π»Π΅Π²-Π¨Π²Π°ΡΡ, Π¨Π°ΠΉ ΠΠ΅Π½-ΠΠ°Π²ΠΈΠ΄
ΠΠ°ΡΠΈΠ½Π½ΠΎΠ΅ ΠΎΠ±ΡΡΠ΅Π½ΠΈΠ΅ β ΠΎΠ΄ΠΈΠ½ ΠΈΠ· ΡΠ°ΠΌΡΡ Π±ΡΡΡΡΠΎ ΡΠ°Π·Π²ΠΈΠ²Π°ΡΡΠΈΡ ΡΡ ΡΠ°Π·Π΄Π΅Π»ΠΎΠ² ΠΈΠ½ΡΠΎΡΠΌΠ°ΡΠΈΠΊΠΈ, Ρ ΠΏΡΠΈΠ»ΠΎΠΆΠ΅Π½ΠΈΡΠΌΠΈ Π² ΡΠ°ΠΌΡΡ ΡΠ°Π·Π½ΡΡ ΠΎΠ±Π»Π°ΡΡΡΡ . Π¦Π΅Π»Ρ ΡΡΠΎΠΉ ΠΊΠ½ΠΈΠ³ΠΈ β ΠΏΠΎΠ·Π½Π°ΠΊΠΎΠΌΠΈΡΡ ΡΠΈΡΠ°ΡΠ΅Π»Ρ Ρ ΡΡΠ½Π΄Π°ΠΌΠ΅Π½ΡΠ°Π»ΡΠ½ΡΠΌΠΈ ΠΏΡΠΈΠ½ΡΠΈΠΏΠ°ΠΌΠΈ ΠΌΠ°ΡΠΈΠ½Π½ΠΎΠ³ΠΎ ΠΎΠ±ΡΡΠ΅Π½ΠΈΡ ΠΈ Ρ Π°ΡΠ°ΠΊΡΠ΅ΡΠ½ΡΠΌΠΈ Π΄Π»Ρ Π½Π΅Π³ΠΎ Π°Π»Π³ΠΎΡΠΈΡΠΌΠΈΡΠ΅ΡΠΊΠΈΠΌΠΈ ΠΏΠ°ΡΠ°Π΄ΠΈΠ³ΠΌΠ°ΠΌΠΈ. ΠΠ½ΠΈΠ³Π° ΡΠΎΠ΄Π΅ΡΠΆΠΈΡ ΠΎΠ±ΡΠΈΡΠ½ΡΠΉ ΡΠ²ΠΎΠ΄ ΠΎΡΠ½ΠΎΠ²ΠΎΠΏΠΎΠ»Π°Π³Π°ΡΡΠΈΡ ΡΠ΅ΠΎΡΠ΅ΡΠΈΡΠ΅ΡΠΊΠΈΡ ΠΈΠ΄Π΅ΠΉ ΠΌΠ°ΡΠΈΠ½Π½ΠΎΠ³ΠΎ ΠΎΠ±ΡΡΠ΅Π½ΠΈΡ ΠΈ ΠΌΠ°ΡΠ΅ΠΌΠ°ΡΠΈΡΠ΅ΡΠΊΠΈΠ΅ Π²ΡΠΊΠ»Π°Π΄ΠΊΠΈ, Π±Π»Π°Π³ΠΎΠ΄Π°ΡΡ ΠΊΠΎΡΠΎΡΡΠΌ ΡΡΠΈ ΠΈΠ΄Π΅ΠΈ ΡΡΠ°Π½ΠΎΠ²ΡΡΡΡ ΠΏΡΠ°ΠΊΡΠΈΡΠ΅ΡΠΊΠΈΠΌΠΈ Π°Π»Π³ΠΎΡΠΈΡΠΌΠ°ΠΌΠΈ. ΠΡΠ»Π΅Π΄ Π·Π° ΠΈΠ·Π»ΠΎΠΆΠ΅Π½ΠΈΠ΅ΠΌ Π±Π°Π·ΠΎΠ²ΡΡ ΠΎΡΠ½ΠΎΠ² Π΄ΠΈΡΡΠΈΠΏΠ»ΠΈΠ½Ρ ΡΠ°ΡΡΠΌΠ°ΡΡΠΈΠ²Π°Π΅ΡΡΡ ΡΠΈΡΠΎΠΊΠΈΠΉ ΡΠΏΠ΅ΠΊΡΡ ΡΠ΅ΠΌ, Π½Π΅ Π½Π°ΡΠ΅Π΄ΡΠΈΡ Π΄ΠΎΡΡΠ°ΡΠΎΡΠ½ΠΎΠ³ΠΎ ΠΎΡΡΠ°ΠΆΠ΅Π½ΠΈΡ Π² ΠΏΡΠ΅Π΄ΡΠ΅ΡΡΠ²ΡΡΡΠΈΡ ΡΡΠ΅Π±Π½ΠΈΠΊΠ°Ρ : Π²ΡΡΠΈΡΠ»ΠΈΡΠ΅Π»ΡΠ½Π°Ρ ΡΠ»ΠΎΠΆΠ½ΠΎΡΡΡ ΠΎΠ±ΡΡΠ΅Π½ΠΈΡ, ΠΏΠΎΠ½ΡΡΠΈΡ Π²ΡΠΏΡΠΊΠ»ΠΎΡΡΠΈ ΠΈ ΡΡΡΠΎΠΉΡΠΈΠ²ΠΎΡΡΠΈ, Π²Π°ΠΆΠ½ΡΠ΅ Π°Π»Π³ΠΎΡΠΈΡΠΌΡ, Π²ΠΊΠ»ΡΡΠ°Ρ ΡΡΠΎΡ Π°ΡΡΠΈΡΠ΅ΡΠΊΠΈΠΉ Π³ΡΠ°Π΄ΠΈΠ΅Π½ΡΠ½ΡΠΉ ΡΠΏΡΡΠΊ, Π½Π΅ΠΉΡΠΎΠ½Π½ΡΠ΅ ΡΠ΅ΡΠΈ ΠΈ ΠΎΠ±ΡΡΠ΅Π½ΠΈΠ΅ ΡΡΡΡΠΊΡΡΡΠΈΡΠΎΠ²Π°Π½Π½ΠΎΠΌΡ Π²ΡΠ²ΠΎΠ΄Ρ, Π° ΡΠ°ΠΊΠΆΠ΅ ΡΠΎΠ²ΡΠ΅ΠΌ Π½Π΅Π΄Π°Π²Π½ΠΈΠ΅ ΡΠ΅ΠΎΡΠ΅ΡΠΈΡΠ΅ΡΠΊΠΈΠ΅ ΠΊΠΎΠ½ΡΠ΅ΠΏΡΠΈΠΈ, Π½Π°ΠΏΡΠΈΠΌΠ΅Ρ, PAC-Π±Π°ΠΉΠ΅ΡΠΎΠ²ΡΠΊΠΈΠΉ ΠΏΠΎΠ΄Ρ ΠΎΠ΄ ΠΈ Π³ΡΠ°Π½ΠΈΡΡ ΡΠΆΠ°ΡΠΈΡ.
π Understanding Machine Learning. From Theory to Algorithms [2015] Shai Shalev-Shwartz, Shai Ben-David
Machine learning is one of the fastest growing areas of computer science, with far-reaching applications. The aim of this textbook is to introduce machine learning, and the algorithmic paradigms it offers, in a principled way. The book provides an extensive theoretical account of the fundamental ideas underlying machine learning and the mathematical derivations that transform these principles into practical algorithms. Following a presentation of the basics of the field, the book covers a wide array of central topics that have not been addressed by previous textbooks. These include a discussion of the computational complexity of learning and the concepts of convexity and stability; important algorithmic paradigms including stochastic gradient descent, neural networks, and structured output learning; and emerging theoretical concepts such as the PAC-Bayes approach and compression-based bounds.