Timur Isachenko

Khotite sozdavat sobstvennye II-prilozhenija, no vas pugaet slozhnost tekhnologij? Eta kniga - prakticheskij gid dlja razrabotchikov, analitikov dannykh i entuziastov, kotorye tolko nachinajut svoj put v mashinnom obuchenii. Vy s nulja osvoite kljuchevye kontseptsii: ot osnov ML i glubokogo obuchenija do arkhitektury transformerov, lezhaschej v osnove sovremennykh LLM. Chto vnutri: * dorozhnaja karta dlja poetapnogo sozdanija II-prilozhenij; * prompt-inzhiniring i rabota s lokalnymi LLM; * tonkaja nastrojka modelej i obogaschenie ikh dannymi; * sozdanie avtonomnykh AI-agentov dlja realnykh zadach; * prakticheskie kejsy: ot intellektualnoj obrabotki SQL do avtomatizatsii raboty s izobrazhenijami. Osobykh znanij ne trebuetsja - dostatochno bazovogo ponimanija Python. Kniga sochetaet neobkhodimuju teoriju s poshagovymi primerami, chtoby vy ne prosto ponjali, a srazu smogli primenit poluchennye znanija na praktike. Stante spetsialistom po generativnomu II uzhe segodnja!

This book covers a verity of topics, including in-memory data grid, highly available service grid, streaming (event processing for IoT and fast data) and in-memory computing use cases from high-performance computing to get performance gains. The book will be particularly useful for those, who have the following use cases:1) You have a high volume of ACID transactions in your system.2) You have database bottleneck in your application and want to solve the problem.3) You want to develop and deploy Microservices in a distributed fashion.4) You have an existing Hadoop ecosystem (OLAP) and want to improve the performance of map/reduce jobs without making any changes in your existing map/reduce jobs.5) You want to share Spark RDD directly in-memory (without storing the state into the disk)7) You are planning to process continuous never-ending streams and complex events of data.8) You want to use distributed computations in parallel fashion to gain high performance.