Python machine learning

There are no silver bullets in algorithm design, and no single algorithmic idea is powerful and flexible enough to solve every computational problem. Nor are there silver bullets in algorithm analysis, as the most enlightening method for analyzing an algorithm often depends on the problem and the application. However, typical algorithms courses rely almost entirely on a single analysis framework, that of worst-case analysis, wherein an algorithm is assessed by its worst performance on any input of a given size. The purpose of this book is to popularize several alternatives to worst-case analysis and their most notable algorithmic applications, from clustering to linear programming to neural network training. Forty leading researchers have contributed introductions to different facets of this field, emphasizing the most important models and results, many of which can be taught in lectures to beginning graduate students in theoretical computer science and machine learning.

Algorithms permeate our lives in numerous ways, performing tasks that until recently could only be carried out by humans. Artificial Intelligence (AI) technologies, based on machine learning algorithms and big-data-powered systems, can perform sophisticated tasks such as driving cars, analyzing medical data, and evaluating and executing complex financial transactions - often without active human control or supervision. Algorithms also play an important role in determining retail pricing, online advertising, loan qualification, and airport security. In this work, Martin Ebers and Susana Navas bring together a group of scholars and practitioners from across Europe and the US to analyze how this shift from human actors to computers presents both practical and conceptual challenges for legal and regulatory systems. This book should be read by anyone interested in the intersection between computer science and law, how the law can better regulate algorithmic design, and the legal ramificatio

The twenty-first century has seen a breathtaking expansion of statistical methodology, both in scope and in influence. 'Big data', 'data science', and 'machine learning' have become familiar terms in the news, as statistical methods are brought to bear upon the enormous data sets of modern science and commerce. How did we get here? And where are we going? This book takes us on an exhilarating journey through the revolution in data analysis following the introduction of electronic computation in the 1950s. Beginning with classical inferential theories - Bayesian, frequentist, Fisherian - individual chapters take up a series of influential topics: survival analysis, logistic regression, empirical Bayes, the jackknife and bootstrap, random forests, neural networks, Markov chain Monte Carlo, inference after model selection, and dozens more. The distinctly modern approach integrates methodology and algorithms with statistical inference. The book ends with speculation on the future direction

Classical computer science textbooks tell us that some problems are 'hard'. Yet many areas, from machine learning and computer vision to theorem proving and software verification, have defined their own set of tools for effectively solving complex problems. Tractability provides an overview of these different techniques, and of the fundamental concepts and properties used to tame intractability. This book will help you understand what to do when facing a hard computational problem. Can the problem be modelled by convex, or submodular functions? Will the instances arising in practice be of low treewidth, or exhibit another specific graph structure that makes them easy? Is it acceptable to use scalable, but approximate algorithms? A wide range of approaches is presented through self-contained chapters written by authoritative researchers on each topic. As a reference on a core problem in computer science, this book will appeal to theoreticians and practitioners alike.

Originating from the authors' own graduate course at the University of North Carolina, this material has been thoroughly tried and tested over many years, making the book perfect for a two-term course or for self-study. It provides a concise introduction that covers all of the measure theory and probability most useful for statisticians, including Lebesgue integration, limit theorems in probability, martingales, and some theory of stochastic processes. Readers can test their understanding of the material through the 300 exercises provided. The book is especially useful for graduate students in statistics and related fields of application (biostatistics, econometrics, finance, meteorology, machine learning, and so on) who want to shore up their mathematical foundation. The authors establish common ground for students of varied interests which will serve as a firm 'take-off point' for them as they specialize in areas that exploit mathematical machinery.

Originating from the authors' own graduate course at the University of North Carolina, this material has been thoroughly tried and tested over many years, making the book perfect for a two-term course or for self-study. It provides a concise introduction that covers all of the measure theory and probability most useful for statisticians, including Lebesgue integration, limit theorems in probability, martingales, and some theory of stochastic processes. Readers can test their understanding of the material through the 300 exercises provided. The book is especially useful for graduate students in statistics and related fields of application (biostatistics, econometrics, finance, meteorology, machine learning, and so on) who want to shore up their mathematical foundation. The authors establish common ground for students of varied interests which will serve as a firm 'take-off point' for them as they specialize in areas that exploit mathematical machinery.

Memory-based language processing - a machine learning and problem solving method for language technology - is based on the idea that the direct reuse of examples using analogical reasoning is more suited for solving language processing problems than the application of rules extracted from those examples. This book discusses the theory and practice of memory-based language processing, showing its comparative strengths over alternative methods of language modelling. Language is complex, with few generalizations, many sub-regularities and exceptions, and the advantage of memory-based language processing is that it does not abstract away from this valuable low-frequency information. By applying the model to a range of benchmark problems, the authors show that for linguistic areas ranging from phonology to semantics, it produces excellent results. They also describe TiMBL, a software package for memory-based language processing. The first comprehensive overview of the approach, this book wi

Inferring the precise locations and splicing patterns of genes in DNA is a difficult but important task, with broad applications to biomedicine. The mathematical and statistical techniques that have been applied to this problem are surveyed and organized into a logical framework based on the theory of parsing. Both established approaches and methods at the forefront of current research are discussed. Numerous case studies of existing software systems are provided, in addition to detailed examples that work through the actual implementation of effective gene-predictors using hidden Markov models and other machine-learning techniques. Background material on probability theory, discrete mathematics, computer science, and molecular biology is provided, making the book accessible to students and researchers from across the life and computational sciences. This book is ideal for use in a first course in bioinformatics at graduate or advanced undergraduate level, and for anyone wanting to kee

Inferring the precise locations and splicing patterns of genes in DNA is a difficult but important task, with broad applications to biomedicine. The mathematical and statistical techniques that have been applied to this problem are surveyed and organized into a logical framework based on the theory of parsing. Both established approaches and methods at the forefront of current research are discussed. Numerous case studies of existing software systems are provided, in addition to detailed examples that work through the actual implementation of effective gene-predictors using hidden Markov models and other machine-learning techniques. Background material on probability theory, discrete mathematics, computer science, and molecular biology is provided, making the book accessible to students and researchers from across the life and computational sciences. This book is ideal for use in a first course in bioinformatics at graduate or advanced undergraduate level, and for anyone wanting to kee

Advances in experimental methods have resulted in the generation of enormous volumes of data across the life sciences. Hence clustering and classification techniques that were once predominantly the domain of ecologists are now being used more widely. This 2006 book provides an overview of these important data analysis methods, from long-established statistical methods to more recent machine learning techniques. It aims to provide a framework that will enable the reader to recognise the assumptions and constraints that are implicit in all such techniques. Important generic issues are discussed first and then the major families of algorithms are described. Throughout the focus is on explanation and understanding and readers are directed to other resources that provide additional mathematical rigour when it is required. Examples taken from across the whole of biology, including bioinformatics, are provided throughout the book to illustrate the key concepts and each technique's potential.

Text mining is a new and exciting area of computer science research that tries to solve the crisis of information overload by combining techniques from data mining, machine learning, natural language processing, information retrieval, and knowledge management. Similarly, link detection – a rapidly evolving approach to the analysis of text that shares and builds upon many of the key elements of text mining – also provides new tools for people to better leverage their burgeoning textual data resources. The Text Mining Handbook presents a comprehensive discussion of the state-of-the-art in text mining and link detection. In addition to providing an in-depth examination of core text mining and link detection algorithms and operations, the book examines advanced pre-processing techniques, knowledge representation considerations, and visualization approaches. Finally, the book explores current real-world, mission-critical applications of text mining and link detection in such varied fields a

A complete resource for finance students, this textbook presents the most common empirical approaches in finance in a comprehensive and well-illustrated manner that shows how econometrics is used in practice, and includes detailed case studies to explain how the techniques are used in relevant financial contexts. Maintaining the accessible prose and clear examples of previous editions, the new edition of this best-selling textbook provides support for the main industry-standard software packages, expands the coverage of introductory mathematical and statistical techniques into two chapters for students without prior econometrics knowledge, and includes a new chapter on advanced methods. Learning outcomes, key concepts and end-of-chapter review questions (with full solutions online) highlight the main chapter takeaways and allow students to self-assess their understanding. Online resources include extensive teacher and student support materials, including EViews, Stata, R, and Python so

A concise but informative overview of AI ethics and policy.Artificial intelligence, or AI for short, has generated a staggering amount of hype in the past several years. Is it the game-changer it's been cracked up to be? If so, how is it changing the game? How is it likely to affect us as customers, tenants, aspiring homeowners, students, educators, patients, clients, prison inmates, members of ethnic and sexual minorities, and voters in liberal democracies? Authored by experts in fields ranging from computer science and law to philosophy and cognitive science, this book offers a concise overview of moral, political, legal and economic implications of AI. It covers the basics of AI's latest permutation, machine learning, and considers issues such as transparency, bias, liability, privacy, and regulation.Both business and government have integrated algorithmic decision support systems into their daily operations, and the book explores the implications for our lives as citizens. For exam

The Strategy and Tactics of Pricing is the most well-established and influential strategic pricing text available, relied on by practitioners and students globally as a core guide for value-based pricing. The book explains how to balance the ability to create and extract value through from markets by managing pricing decisions in a more strategic and profitable manner. Rather than calculating prices to cover costs or to achieve sales goals, readers will learn to frame more strategic choices that proactively influence customer perceptions of value, manage internal costs, and profitably shift demand curves.This edition features new discussions on harnessing concepts from behavioral economics as well as a refined "value cascade" to help organize the topics covered in this book. Readers will also benefit from:1.Major revisions to more than a third of the chapters, including an expanded discussion of the role of artificial intelligence and machine learning analytics tools to assist in the e

Over the last half century, "smartness"―the drive for ubiquitous computing―has become a mandate: a new mode of managing and governing politics, economics, and the environment.Smart phones. Smart cars. Smart homes. Smart cities. The imperative to make our world ever smarter in the face of increasingly complex challenges raises several questions: What is this "smartness mandate?" How has it emerged, and what does it say about our evolving way of understanding―and managing―reality? How have we come to see the planet and its denizens first and foremost as data-collecting instruments? In The Smartness Mandate, Orit Halpern and Robert Mitchell radically suggest that "smartness" is not primarily a technology, but rather an epistemology. Through this lens, they offer a critical exploration of the practices, technologies, and subjects that such an understanding relies upon―above all, artificial intelligence and machine learning. The authors approach these not simply as techniques for solving pr

The entanglements of people and data, code and space, knowledge and power: how data and algorithms shape the world―and shape us within that world.With the emergence of a post-truth world, we have witnessed the dissolution of the common ground on which truth claims were negotiated, individual agency enacted, and public spheres shaped. What happens when, as Nietzsche claimed, there are no facts, but only interpretations? In this book, Mark Shepard examines the entanglements of people and data, code and space, knowledge and power that have produced an uncommon ground―a disaggregated public sphere where the extraction of behavioral data and their subsequent processing and sale have led to the emergence of micropublics of ever-finer granularity. Shepard explores how these new post-truth territories are propagated through machine learning systems and social networks, which shape the public and private spaces of everyday life. He traces the balkanization and proliferation of online news and t

An accessible analysis of the new forms of work whose seismic changes will increasingly determine the future of capitalism Automation and the decline in industrial employment have lead to rising fears of a workless future. But what happens when your work itself is the thing that will make your job obsolete? In the past few years, online crowdworking platforms - like Amazon's Mechanical Turk and Clickworker - have become an increasingly important source of work, particularly for those in the Global South. Here, small tasks are assigned to people online, and are often used to train algorithms to spot patterns, patterns through machine learning those same algorithms will then be able to spot more effectively than humans. Used for everything from the mechanics of self-driving cars to Google image search, this is an increasingly powerful part of the digital ecomomy. But what happens to work when it makes itself obsolete. In this stimulating work that blends political economy, studies of con

This book integrates the foundations of quantum computing with a hands-on coding approach to this emerging field; it is the first to bring these strands together in an updated manner. This work is suitable for both academic coursework and corporate technical training.The second edition includes extensive updates and revisions, both to textual content and to the code. Sections have been added on quantum machine learning, quantum error correction, Dirac notation and more. This new edition benefits from the input of the many faculty, students, corporate engineering teams, and independent readers who have used the first edition.This volume comprises three books under one cover: Part I outlines the necessary foundations of quantum computing and quantum circuits. Part II walks through the canon of quantum computing algorithms and provides code on a range of quantum computing methods in current use. Part III covers the mathematical toolkit required to master quantum computing. Additional reso

The increased and widespread availability of large network data resources in recent years has resulted in a growing need for effective methods for their analysis. The challenge is to detect patterns that provide a better understanding of the data. However, this is not a straightforward task because of the size of the data sets and the computer power required for the analysis. The solution is to devise methods for approximately answering the questions posed, and these methods will vary depending on the data sets under scrutiny. This cutting-edge text introduces biological concepts and biotechnologies producing the data, graph and network theory, cluster analysis and machine learning, before discussing the thought processes and creativity involved in the analysis of large-scale biological and medical data sets, using a wide range of real-life examples. Bringing together leading experts, this text provides an ideal introduction to and insight into the interdisciplinary field of network da

Networks are everywhere: networks of friends, transportation networks and the Web. Neurons in our brains and proteins within our bodies form networks that determine our intelligence and survival. This modern, accessible textbook introduces the basics of network science for a wide range of job sectors from management to marketing, from biology to engineering, and from neuroscience to the social sciences. Students will develop important, practical skills and learn to write code for using networks in their areas of interest - even as they are just learning to program with Python. Extensive sets of tutorials and homework problems provide plenty of hands-on practice and longer programming tutorials online further enhance students' programming skills. This intuitive and direct approach makes the book ideal for a first course, aimed at a wide audience without a strong background in mathematics or computing but with a desire to learn the fundamentals and applications of network science.

A heartwarming, educational picture book that allows parents to tell their kids how much they love them while also teaching them interesting facts about the world.';I love you.'';I love you more.'Almost every parent and child play this game of who loves who the most. Wall decorations say: ';I Love You More' and even movies have characters who join in with this debate. This book will help children understand once and for all how much they are lovedfrom hereto the sun and beyond.How much you love someone isn't easy to quantify, but I Love You to the Sun and Beyondis here to tell your children just how much you love them through more than twenty wonderful and wacky analogies. From python hugs to Nikola Tesla to the Mariana Trench, your little reader will learn all about the world and the amazing things in it while also learning the most important thing of all: how much you care.

CELEBRATE FOOTBALL EVERY DAY OF THE YEAR WITH THE BRAND-NEW BOOK IN THE BESTSELLING SERIES WHERE FOOTBALL AND FACTS COME TOGETHER IN A DREAM TEAM FORMATION. THE PERFECT GIFT FOR ALL YOUNG FANS."The ultimate football yearbook where you can discover a new fun footie fact for every day of the year."-The Week JuniorWelcome to Football School Facts! It’s a book of facts and so let’s start with an important one: football is the best sport in the world.- Did you know that Erling Haaland is a record-breaking goalscoring machine?- That a player was once sent off for farting on the pitch?- Or that Diego Maradona has a religion named after him?Discover all this and much, much more all about your favourite players, great goals, super stadiums and marvellous mascots – the perfect gift for all young fans and their families to enjoy."An engaging, fun read that will keep children laughing, learning and dreaming of the pitch."- Women's Weekly"We love this series!"-Match of the Day Weekly***There’s a wh

Available in paperback! A young chapter book series starter about a chicken who loves math, science, and learning new things--by New York Times bestselling author Nancy Krulik. Perfect for fans of Unlimited Squirrels and Bumble and Bee. Chirpy is a young chicken stuck in the family coop. But she's not like the other chickens who just sit around peck peck pecking all day. She's intrigued by the children who come home from a place called school. They always look so happy! (Well, most days.) So Chirpy sneaks onto the bus one morning, hides in the classroom . . . and discovers a true love of math. When she shares what she's learned with the other chickens, they think she's one kernel short of a cob. Even so, Chirpy is determined to find a formula for fowl success by pecking away. But when a hungry fox tries to attack the coop, can she find the equation for a simple solution? With lively two-color art throughout, plus a fun hands-on simple machine activity, this eggs-ellent young chapter bo

近年來，人工智能與機器人在全世界範圍內備受關注。但是從2014年開始，國際權威調研機構高德納諮詢公司(Gartner)每年公佈的十大技術中，“大數據”這樣的詞語已經不再出現了。這不是因為“大數據”不再重要，而是意味著自2015年以後，“大數據”已經包含在十大技術裡，或者已經成為這些技術的基礎。“大數據”不僅可以用於構建和應用分析模型，還可以應用於機器學習(Machine Learning)、人工智能等諸多領域。本書從多種觀點出發，闡述了對大數據分析的理解和在環境、大數據企劃與設計層面上需要考慮的問題。

《強化學習基礎、原理與應用》循序漸進地講解了使用Python語言實現強化學習的核心算法開發的知識，內容涵蓋了數據處理、算法、大模型等知識，並通過具體實例的實現過程演練了各個知識點的使用方法和使用流程。《強化學習基礎、原理與應用》共分為17章，主要內容包括強化學習基礎、馬爾可夫決策過程、蒙特卡洛方法、Q-learning與貝爾曼方程、時序差分學習和SARSA算法、DQN算法、DDQN算法、競爭DQN算法、REINFORCE算法、Actor-Critic算法、PPO算法、TRPO算法、連續動作空間的強化學習、值分布式算法、基於模型的強化學習、多智能體強化學習實戰：Predator-Prey 遊戲及自動駕駛系統。本書內容簡潔而不失技術深度，以極簡的文字介紹了複雜的案例，易於閱讀和理解。《強化學習基礎、原理與應用》適用於已經瞭解Python語言基礎語法的讀者，想進一步學習強化學習、機器學習、深度學習及相關技術的讀者，還可作為大專院校相關專業的師生用書和培訓機構的教材使用。

這本書帶領讀者重新思考人工智慧的背後代價。不只是程式與演算法，AI的運作牽涉到龐大的自然資源、人力勞動與個人資料。作者凱特・克勞佛以十多年研究為基礎，揭示AI如何重新分配權力、加劇不平等，並對民主與環境造成深遠影響，是一部兼具深度與警示意義的作品。The hidden costs of artificial intelligence—from natural resources and labor to privacy, equality, and freedom“This study argues that [artificial intelligence] is neither artificial nor particularly intelligent. . . . A fascinating history of the data on which machine-learning systems are trained.”—New Yorker“A valuable corrective to much of the hype surrounding AI and a useful instruction manual for the future.”—John Thornhill, Financial Times“It’s a masterpiece, and I haven’t been able to stop thinking about it.”—Karen Hao, senior editor, MIT Tech ReviewWhat happens when artificial intelligence saturates political life and depletes the planet? How is AI shaping our understanding of ourselves and our societies? Drawing on more than a decade of research, award‑winning scholar Kate Crawford reveals how AI is a technology of extraction: from the minerals drawn from

特色1. 數據處理和數據分析並重。針對金融大數據結構複雜、數據源和格式變換大的特點，充分講述SAS軟件DATA步強大的數據處理功能，強化金融數據處理內容。2. 將SAS數據分析能力強和R和Python靈巧和業界流行的特點相結合，建立融合SAS和R及Python的數據處理和分析教材構架，進行教學大綱、授課教案到教材、案例集和習題集等課程要件建設。3. 以《金融計量經濟學》為知識依托，以海通證券金融工程部、天風證券金融工程部、等有名券商量化金融策略為具體案例內容，以權益（股票）市場和債券（固定收益）市場為主要應用領域，以日數據（daily data）為主、高頻日內數據（intraday data）為輔，建立從數據搜集到數據清理、從投資組合到交易策略和算法交易等金融量化方法的教學案例。創新點1. 填補國內教材空白。作為一款權威的數據處理和統計分析軟件，多年來SAS在國內（尤其是銀行系統）得到了廣泛應用。已出版的教材多以操作和數據處理編程為主，針對金融數據處理和分析的書籍並不多見，尤其講解金融數據分析的SAS過程步（Proc step）的教材難以見到。本教材擬對分析金融時間序列的SAS過程進行詳細和全面的介紹，充分揭示SAS在處理和分析金融時間序列數據上的優勢，填補國內教材空白。2.SAS Viya平臺介紹和R、Python的軟件融合。SAS Viya 2016年推出以來，得到了很快的發展，出現了基於SAS Viya 云分析服務CAS的很多應用，國內一些金融機構也採用了SAS Viya構建自己的數據分析平臺。但國內介紹SAS Viya的書很少，沒有發現介紹利用SAS Viya中的ACTION進行金融數據分析的書籍。對SAS Viya的介紹以及利用SAS Viya中的Econometrics8.4 ACTION、Visal Statistical Analysis ACTION、Deep Learning ACTION等進行金融數據處理和分析的內容，是本教材的創新之處。

深度學習 最佳入門邁向AI專題實戰 ★★★★★【深度學習】★★★★★ ☆☆☆☆☆【理論】+【實作】☆☆☆☆☆ 這是目前市面上講解【深度學習(Deep Learning)】從基礎到應用最完整的書籍，從基礎數學與統計開始，將演算法的原理解釋得更簡易清晰，協助讀者跨入 AI 的門檻，為避免流於空談，盡量增加應用範例，希望能達到即學即用。多位試閱本書內容的專家與學者全部皆給【五顆星】滿分評價。 整本書採用【最新版TensorFlow】+【大量圖片輔助】，+ 【完整理論解說】+【Python程式實作】以原理與實作，講解下列最熱門的AI主題。 ☆【神經網路(NN)】 ☆【卷積神經網路(CNN)】 ☆【物件偵測(YOLO)】 ☆【光學文字辨識(OCR)】 ☆【車牌辨識(ANPR)】 ☆【人臉辨識】 ☆【生成對抗網路 (GAN)】 ☆【深度偽造 (DeepFake)】 ☆【自然語言處理(NLP)】 ☆【聊天機器人(ChatBot)】 ☆【語音辨識(ASR)】 ☆【強化學習(RL)】 讀者只要遵循本書步驟學習相信必可以徹底認識人工智慧、機器學習與深度學習觀念，邁向浩瀚領域。

人工智慧（AI）將改變人類與所有產業的生態。 如果你對人工智慧，沒有全面的了解，那就跟不上時代了。很多影響人類的科技發展，都無法做出正確的判斷。 一個知名的投資專家說，比起5G，人人手上有，處處可見基地台，AI只有少數大公司用得上，到底有無潛力？有！但是不要想得太美了。 他說的對不對？很難判斷嗎？讀完本書，你就會找到正確的解答。 其實AI有三種，一種是雲端，就是連到那幾家大公司的機房，用他們大的嚇死人的算力。 一種是在本地運算，如汽車的自動駕駛。第三種則是運用在最前端的偵測裝置，以求最快的反應時間。 所以你說AI只有幾家大公司用得上，好像也沒有那麼對。 所以你要把它想得美一點，它是平地一聲雷，輝達、台積電的股價都應該後面加一千個零，是嗎？ 但是你知道有資訊科技以來，人類至少經過三次AI的浪潮。很多公司運用AI運用得嚇嚇叫，如文藝復興基金，用機器學習投資，20年來平均的年化報酬率遠勝巴菲特。 所以你說AI前程遠大！很OK，但它說他橫空出世？倒也未必，它只是一個連續的改善過程！ 當然有關AI最誇張的是想像是《魔鬼終結者》，一個是幹掉想毁滅人類的傢伙，而且他可以和人腦一樣的運作。不過有的人是殺人魔，有的人是慈善家。不知可以和人腦一樣運作的AI是慈善家或是殺人魔？ AI的形式有很多種，從撰寫大量複雜的函式來實現人工智慧的專家系統，到以大量資料反求智慧判定函式的演算法，如支援向量機（Support Vector Machine, SVM）、決策樹（Decision Tree）等，此領域統稱為機器學習（Machine Learning, ML），而運用神經網路技術，將網路的節點深度擴展延伸，以獲得更好的智慧判定效果，則稱為深度學習（Deep Learning, DL）。 你越了解AI的技術背景，就越能掌握它未來對人類的影響。如果你想投資AI相關產業，就更是需要深入了解了。 任何資訊科技的運用都有兩個層面，軟體以及執行軟體的硬體。本書除了說明AI運用的基本原理之外，也將詳細說明有關AI的軟體及硬體產業鏈。對一個投資人而言，完整的了解一個產業的上下游關係，是十分必要的。 總不能輝達業績創新高，而你完全沒有概念台積電會好還是不好吧？ 本書以圖文對照的方式，讓你對AI有清楚的認識。不論投資、或生活，可以在新科技浪潮中，穩定前行。 本書特色 ◎100個單元，

多智能體強化學習(Multi-Agent Reinforcement Learning, MARL)是機器學習中的一個領域，研究多個智能體如何在共享環境中學習最優的交互方式。這一領域在現代生活中有著廣泛的應用，包括自動駕駛、多機器人工廠、自動化交易和能源網絡管理等。 本書是一部系統闡述多智能體強化學習理論與技術的權威著作，清晰而嚴謹地介紹了MARL的模型、解決方案概念、算法思想、技術挑戰以及現代方法。書中首先介紹了該領域的基礎知識，包括強化學習理論和算法的基礎、交互式博弈模型、博弈中的不同解決方案概念以及支撐MARL研究的算法思想。隨後，書中詳細介紹了利用深度學習技術的現代MARL算法，涵蓋集中訓練與分散執行、價值分解、參數共享和自博弈等思想。本書還附帶了一個用Python編寫的MARL代碼庫，其中包括自包含且易於閱讀的MARL算法實現。 本書技術內容以易於理解的語言解釋，並通過大量示例進行說明，既為初學者闡明了MARL的概念，也為專業的讀者提供了高層次的見解。

「作者在上市 IC 公司上班，每天面對 real world problems。探索如何建立輕量深度學習網路以及發展更有效率的學習方式是他每天的工作。這是一本學理及實務兼具的好工具書。」 － 中央研究院資訊科學研究所所長 廖弘源博士 推薦[搭起 AI 與統計的橋樑]原本統計學與人工智慧是兩個完全不同的領域，然而兩者在近代都有了新的發展進而產生連結。在人工智慧中導入機率與統計的觀念，讓電腦具有自己找出數據之間的關聯性並試圖解決問題的能力，因而出現機器學習 (machine learning) ，再加上電腦計算能力的大幅提升，解決多層類神經網路和大數據之間聯繫性的可能，進而衍生出現今最熱門的深度學習 (deep learning)。不過，大部分電腦相關科系出身的人並不熟悉統計學，因此在更上一層樓的時候容易遇到障礙。有鑒於此，小編在推出《機器學習的數學基礎》(天瓏專業書店年度暢銷第一名) 一書之後，就積極開發 AI 與統計學相關的書籍。在尋尋覓覓之後請到擅長統計與機器學習的黃志勝博士出馬撰寫《機器學習的統計基礎》，首要之務就是讓讀者不要視統計為畏途，因此在書中設計大量範例以降低學習難度，務求讀得懂、做得出來才容易吸收，進而搭好統計與機器學習的橋樑。如果自覺數學已經還給老師了也不用擔心，可以將本書搭配《機器學習的數學基礎》一併完整學習。[學會統計, 由混亂到清晰]本書從讀者在高中就學過的集合與機率論開始，帶您快速複習一遍，並將容易混淆之處多多舉例說明，並將以前似懂非懂的隨機變數、機率分布等觀念再解釋得更清楚。接下來就進入專有名詞特別多的統計學，這也是造成許多人暈頭轉向之處。特別是樣本估計、信賴區間、顯著水準、信心水準、t-分布、假設檢定...等讓人一個頭兩個大的主題，更是務求清楚明瞭。當然本書不可能把完整的統計學全都搬進來，此處只介紹機器學習、深度學習需要用到的統計基礎知識，縮短您的學習時間。然後就進入機器學習的重頭戲，從資料前處理到迴歸、分類模型的建立，以及當數據的特徵數過多時的 PCA、LDA 統計降維法。從類神經網路開始進入深度學習的範疇，包括前向傳遞、梯度下降法與倒傳遞學習法的手算實作，幫助讀者一步步建立深度學習的演算邏輯，並利用參數常規化解決模型過擬合 (over-fitting) 的問題。最後，導入模型評估，例如二元、多元分類模型評估指標、迴歸模型評估指標、4