Deep Learning with Python

A parent with ASD can provide his or her children with deep love and devoted support, along with a perspective on the world that is wonderfully unique. At the same time, the emotional and physical dem

深度學習正日益深刻地滲入我們的生活，從建議內容到在任務關鍵型和安全關鍵型應用中發揮核心作用，其影響無所不在。然而，隨著這些算法影響力的逐漸擴大，人們對於依賴這些算法的系統安全性和魯棒性的擔憂也日益加劇。簡言之，傳統的深度學習方法往往難以察覺自身的知識邊界，即它們“不知其所不知”。貝葉斯深度學習(Bayesian Deep Learning，BDL)領域包含一系列利用深度網絡進行近似貝葉斯推理的方法。這些方法通過揭示模型對其預測結果的置信度，增強了深度學習系統的魯棒性，使我們能夠更謹慎地將模型預測融入實際應用中。《Python貝葉斯深度學習》將引領你踏入迅速發展的不確定性感知深度學習領域，助你深入理解不確定性估計在構建魯棒性的機器學習系統中的重要價值。你將學習多種流行的BDL方法，並通過涵蓋多種應用場景的Python實用示例來掌握這些方法的實現技巧。讀完本書後，你將深刻理解BDL及其優勢，並能夠為更安全、更魯棒的深度學習系統開發貝葉斯深度學習模型。主要內容：● 了解貝葉斯推理和深度學習的優缺點● 了解貝葉斯神經網絡(Bayesian Neural Network，BNN)的基本原理● 了解主要貝葉斯神經網絡實現/近似之間的差異● 了解生產環境中概率深度神經網絡的優勢● 在Python代碼中實現各種貝葉斯深度學習方法● 運用貝葉斯深度學習方法解決實際問題● 學習如何評估貝葉斯深度學習方法並為特定任務選擇最佳方法● 在實際深度學習應用中處理“分布外”數據

Machine learning-a computer's ability to learn-is transforming our world: it is used to understand images, process text, make predictions by analyzing large amounts of data, and much more. It can be used in nearly every industry to improve efficiency and help stakeholders make better decisions. Whatever your industry or hobby, chances are that these modern artificial intelligence methods will be useful to you as well.Introduction to Machine Learning weaves reproducible coding examples into explanatory text to show what machine learning is, how it can be applied, and how it works. Perfect for anyone new to the world of AI or those looking to further their understanding, the text begins with a brief introduction to the Wolfram Language, the programming language used for the examples throughout the book. From there, readers are introduced to key concepts before exploring common methods and paradigms such as classification, regression, clustering, and deep learning. The math content is kep

Along with updating all chapters and Python code examples, the second edition of this bestseller includes new chapters on Gaussian processes, Boltzmann machines, and deep belief networks. It also revi

This book introduces artificial neural networks to students and professionals. It covers the theory and applications in statistical learning methods with concrete Python code examples.

A high school student can create deep Q-learning code to control her robot, without any understanding of the meaning of 'deep' or 'Q', or why the code sometimes fails. This book is designed to explain the science behind reinforcement learning and optimal control in a way that is accessible to students with a background in calculus and matrix algebra. A unique focus is algorithm design to obtain the fastest possible speed of convergence for learning algorithms, along with insight into why reinforcement learning sometimes fails. Advanced stochastic process theory is avoided at the start by substituting random exploration with more intuitive deterministic probing for learning. Once these ideas are understood, it is not difficult to master techniques rooted in stochastic control. These topics are covered in the second part of the book, starting with Markov chain theory and ending with a fresh look at actor-critic methods for reinforcement learning.

Accurate, robust and fast image reconstruction is a critical task in many scientific, industrial and medical applications. Over the last decade, image reconstruction has been revolutionized by the rise of compressive imaging. It has fundamentally changed the way modern image reconstruction is performed. This in-depth treatment of the subject commences with a practical introduction to compressive imaging, supplemented with examples and downloadable code, intended for readers without extensive background in the subject. Next, it introduces core topics in compressive imaging – including compressed sensing, wavelets and optimization – in a concise yet rigorous way, before providing a detailed treatment of the mathematics of compressive imaging. The final part is devoted to recent trends in compressive imaging: deep learning and neural networks. With an eye to the next decade of imaging research, and using both empirical and mathematical insights, it examines the potential benefits and the

This lucid, accessible introduction to supervised machine learning presents core concepts in a focused and logical way that is easy for beginners to follow. The author assumes basic calculus, linear algebra, probability and statistics but no prior exposure to machine learning. Coverage includes widely used traditional methods such as SVMs, boosted trees, HMMs, and LDAs, plus popular deep learning methods such as convolution neural nets, attention, transformers, and GANs. Organized in a coherent presentation framework that emphasizes the big picture, the text introduces each method clearly and concisely “from scratch” based on the fundamentals. All methods and algorithms are described by a clean and consistent style, with a minimum of unnecessary detail. Numerous case studies and concrete examples demonstrate how the methods can be applied in a variety of contexts.

This lucid, accessible introduction to supervised machine learning presents core concepts in a focused and logical way that is easy for beginners to follow. The author assumes basic calculus, linear algebra, probability and statistics but no prior exposure to machine learning. Coverage includes widely used traditional methods such as SVMs, boosted trees, HMMs, and LDAs, plus popular deep learning methods such as convolution neural nets, attention, transformers, and GANs. Organized in a coherent presentation framework that emphasizes the big picture, the text introduces each method clearly and concisely “from scratch” based on the fundamentals. All methods and algorithms are described by a clean and consistent style, with a minimum of unnecessary detail. Numerous case studies and concrete examples demonstrate how the methods can be applied in a variety of contexts.

What type of questioning invigorates and sustains productive discussions?That's what Jackie Acree Walsh and Beth Dankert Sattes ask as they begin a passionate exploration of questioning as the beating heart of thoughtful discussions. Questioning and discussion are important components of classroom instruction that work in tandem to push learning forward and move students from passive participants to active meaning-makers.Walsh and Sattes argue that the skills students develop through questioning and discussion are critical to academic achievement, career success, and active citizenship in a democratic society. They also have great potential to engage students at the highest levels of thinking and learning.The extent to which this potential is realized, of course, depends on individual teachers who embrace these practices, make them their own, and realize that this process requires a true partnership with students.With that in mind, Questioning for Classroom Discussion presents and anal

Immerse yourself in fascinating facts about water! This comprehensive yet accessible exploration of water will help young readers understand many aspects of one of our planet's most precious resources - and how they can protect it. A friendly water droplet character guides children through topics ranging from melting and freezing to the ways in which water literally shapes the Earth. Tales by storytellers from around the world are sprinkled through the book, highlighting the variety of ways in which global cultures value water. The engaging format includes gatefolds and booklets with hands-on activity ideas for learning about and protecting water. Topics covered include: The importance of water to life How much of the planet is made of water Where in the world water is located Freezing, melting and evaporation The water cycle Why animals and plants need water Salt water versus fresh water environments Uses for water, including water as a source of renewable energy Water conservation an

Through a series of recent breakthroughs, deep learning has boosted the entire field of machine learning. Now, even programmers who know close to nothing about this technology can use simple, efficien

With a machine learning approach and less focus on linguistic details, this gentle introduction to natural language processing develops fundamental mathematical and deep learning models for NLP under a unified framework. NLP problems are systematically organised by their machine learning nature, including classification, sequence labelling, and sequence-to-sequence problems. Topics covered include statistical machine learning and deep learning models, text classification and structured prediction models, generative and discriminative models, supervised and unsupervised learning with latent variables, neural networks, and transition-based methods. Rich connections are drawn between concepts throughout the book, equipping students with the tools needed to establish a deep understanding of NLP solutions, adapt existing models, and confidently develop innovative models of their own. Featuring a host of examples, intuition, and end of chapter exercises, plus sample code available as an onli

With chapters based on real situations outlining practical strategies, this guide shows you how formative teaching, learning and assessment can enrich day-to-day teaching, and ensure deep and sustaine

With chapters based on real situations outlining practical strategies, this guide shows you how formative teaching, learning and assessment can enrich day-to-day teaching, and ensure deep and sustaine

正宗Keras大神著作再次降臨！近10年來，深度學習為人工智慧領域帶來了出色的進展，也解鎖了許多有趣的新功能，如：機器翻譯、影像識別、物體定位等不一而足。毫不誇張地說，深度學習已迅速成為每位軟體開發者必備的武器。此外，諸如Keras和TensorFlow等先進的工具，也消除了普通人與深度學習之間的隔閡。即使你只有高中程度的數學知識，且甚至沒有資料科學的相關背景，也依舊可以透過這些工具來建構有趣的深度學習應用。本書由 Keras 創始者親自撰寫，沒人比他更了解Keras這套工具，雖然如此，但這並不是一本 Keras 的使用手冊，而是帶你從頭開始探索深度學習，進而拓展對深度學習理解的經典之作。你也將從中明瞭解決機器學習問題的標準作業流程，以及未來實務上如何克服可能遇到的問題。本書前一版在全世界都獲得非常高的評價，並被翻譯成12種語言，到現在仍是技術社群推薦必讀的深度學習入門書。不過深度學習技術在這短短幾年有巨大的進展，因此第二版作者新增了許多常見任務的實作專案，例如：影像分割、時間序列預測、機器翻譯等。另外，作者還加入了當前熱門技術的介紹，如attention機制、Transformer架構、KerasTuner等，並搭配實作案例來加深讀者的理解。由於第二版的內容修改幅度極大，因此中文版重新編譯，由業內專家進行翻譯、審閱，在專有名詞的說法和敘述，都更加符合國內業界的習慣用語。無論你是從業中的機器學習工程師、軟體開發人員，還是資訊科系學生，本書的內容都會對你有所幫助。【重磅推薦】 「掌握本質， 了解其所能與不能， 是面對技術快速迭代、世局難以預測的鑰匙。本書就是開啟深度學習的一把鑰匙。」 ——鴻海研究院執行長 李維斌「對於想熟悉 Keras和Tensorflow的技術人來說， 是一本極佳的入門學習書， 而對於不熟悉技術只想一窺門道的人來說， 結構井然的邏輯和極為通暢易讀的寫作方式， 大大降低了非技術出身如我輩的學習門檻。」 ——台灣人工智慧科技基金會執行長 溫怡玲「Keras大神親自出手將最新的發展及其具體應用範例帶到我們面前， 在AI產業界來說， 這是極其重要的大事， 不可等閒視之， 而且是由在 AI領域著墨很深、實踐經驗豐富的黃逸華數據長主持翻譯與審閱工作， 更讓我們充滿期待。」 ——台灣人工智慧協會副理事長 黃國寶「大神再次出手， 這是AI產業化的高光時刻， 很榮幸