Mathematical Methodologies in Pattern Recognition and Machine Learning

這是一本介紹如何應用大數據和機器學習技術來解決投資問題並提高投資績效的專著。近年來，機器學習和數據科學在投資中發揮著越來越大的作用。從本質上講，機器學習模型在挖掘數據背後的非線性關係上要強于傳統模型。借助機器學習和大數據，投資經理能夠做出以往傳統模型無法實現的預測，進而做出明智的決策。然而，在投資中，並不是所有的數據集和機器學習技術都對金融應用有用，也不是所有的機器學習技術都可以“即插即用”。《大數據、機器學習與量化投資》這本書由資深量化分析專家托尼‧吉達主編，彙集了多位業內頗具影響力的專家學者的前沿分享，闡釋如何應用大數據和機器學習技術來解決投資問題並提高投資績效。這本書共有13章，理論嚴謹，案例豐富，內容涵蓋機器學習在投資管理中的應用現狀和前景、另類數據和大數據在宏觀交易中的應用、處理大數據集的難點和解決方案、挖掘社交媒體數據集分析企業文化、使用自然語言處理技術進行投資者情緒分析、基於支持向量回歸的全球戰術性資產配置策略、強化學習和深度學習在投資組合優化中的應用等主題，可以作為量化投資從業者、金融算法研究人員、高等院校計算機專業和金融工程專業的師生以及機器學習愛好者的參考用書。

Based on the 4G TD-LTE (Time Division-Long Term Evolution) technology, this book uses the modularity-learning mode and the TD-LTE eNodeB equipment of Datang Mobile Company to give a comprehensive instruction about the hardware structure, device opening and setting, equipment maintenance, etc. through different tasks arrangement. This book has three training parts. The first part is the TD-LTE wireless technology, the second one is the recognition of TD-LTE products, and the third one is the operating and maintenance of the base stations. Through the learning of the three training parts, the readers can have a good knowledge of the basic setting and maintenance of a 4G base station, as well as a sound understanding of the structure installation and testing of the hardware, and the starting configuration and testing of the base devices. They can understand the basic knowledge involved in running and testing the mobile communication system. The book aims to train the high-qualified talent

本書作為數據挖掘的入門讀物，基於真實的數據集進行案例實戰，使用Python數據科學庫，從數據預處理開始一步步介紹數據建模和數據挖掘的過程。主要介紹了數據挖掘的基礎知識、基本工具和實踐方法，通過循序漸進地講解算法，帶領讀者輕鬆踏上數據挖掘之旅。本書採用理論與實踐相結合的方式，呈現了如何使用邏輯回歸進行環境數據檢測，如何使用HMM進行中文分詞，如何利用卷積神經網絡識別雷達剖面圖，如何使用循環神經網絡構建聊天機器人，如何使用樸素貝葉斯算法進行破產預測，如何使用DCGAN網絡進行人臉生成等。本書也涉及神經網絡、在線學習、強化學習、深度學習和大數據處理等內容。本書以人工智能主流編程語言Python 3版本作為數據分析與挖掘實戰的應用工具，從Pyhton的基礎語法開始，陸續介紹了NumPy數值計算、Pandas數據處理、Matplotlib數據可視化、爬蟲和Sklearn數據挖掘等內容。全書共涵蓋16個常用的數據挖掘算法和機器學習實戰項目。通過學習本書內容，讀者可以掌握數據分析與挖掘的理論知識及實戰技能。

This book provides a comprehensive foundation of machine learning. To answer the questions of what to learn, how to learn, what to get from learning, and how to evaluate, as well as what is meant by learning, the book focuses on the fundamental basics of machine learning, its methodology, theory, algorithms, and evaluations, together with some philosophical thinking on comparison between machine learning and human learning for machinery intelligence.The book is organized as follows: Introduction (Chapter 1), Evaluation (Chapter 2), Supervised learning (Chapters 3, 4, and 5), Unsupervised learning (Chapter 6), Representation learning (Chapter 7), Problem decomposition (Chapter 8), Ensemble learning (Chapter 9), Deep learning (Chapter 10), Application (Chapter 11), and Challenges (Chapter 12).The book can be used as a textbook for college, undergraduate, graduate and PhD students majored in computer science, automation, electronic engineering, communication, ect. It can also be used as