Deep Learning


Book Description

An introduction to a broad range of topics in deep learning, covering mathematical and conceptual background, deep learning techniques used in industry, and research perspectives. “Written by three experts in the field, Deep Learning is the only comprehensive book on the subject.” —Elon Musk, cochair of OpenAI; cofounder and CEO of Tesla and SpaceX Deep learning is a form of machine learning that enables computers to learn from experience and understand the world in terms of a hierarchy of concepts. Because the computer gathers knowledge from experience, there is no need for a human computer operator to formally specify all the knowledge that the computer needs. The hierarchy of concepts allows the computer to learn complicated concepts by building them out of simpler ones; a graph of these hierarchies would be many layers deep. This book introduces a broad range of topics in deep learning. The text offers mathematical and conceptual background, covering relevant concepts in linear algebra, probability theory and information theory, numerical computation, and machine learning. It describes deep learning techniques used by practitioners in industry, including deep feedforward networks, regularization, optimization algorithms, convolutional networks, sequence modeling, and practical methodology; and it surveys such applications as natural language processing, speech recognition, computer vision, online recommendation systems, bioinformatics, and videogames. Finally, the book offers research perspectives, covering such theoretical topics as linear factor models, autoencoders, representation learning, structured probabilistic models, Monte Carlo methods, the partition function, approximate inference, and deep generative models. Deep Learning can be used by undergraduate or graduate students planning careers in either industry or research, and by software engineers who want to begin using deep learning in their products or platforms. A website offers supplementary material for both readers and instructors.




A Connected Curriculum for Higher Education


Book Description

Is it possible to bring university research and student education into a more connected, more symbiotic relationship? If so, can we develop programmes of study that enable faculty, students and ‘real world’ communities to connect in new ways? In this accessible book, Dilly Fung argues that it is not only possible but also potentially transformational to develop new forms of research-based education. Presenting the Connected Curriculum framework already adopted by UCL, she opens windows onto new initiatives related to, for example, research-based education, internationalisation, the global classroom, interdisciplinarity and public engagement. A Connected Curriculum for Higher Education is, however, not just about developing engaging programmes of study. Drawing on the field of philosophical hermeneutics, Fung argues how the Connected Curriculum framework can help to create spaces for critical dialogue about educational values, both within and across existing research groups, teaching departments and learning communities. Drawing on vignettes of practice from around the world, she argues that developing the synergies between research and education can empower faculty members and students from all backgrounds to contribute to the global common good.




Learning to Lead, Leading to Learn


Book Description

SPECIAL INTRODUCTORY PRICING: Enjoy first-week pricing of $18.95 on paperback books! Regular retail pricing of $23.95 becomes effective on July 22nd. It all began with the initial chance meeting of this book's author, Katie Anderson, and the book's subject, Isao Yoshino. She was an American leadership coach and consultant in her mid-career, with a newfound love of Japanese culture. He was an accomplished Japanese people-centered leader at the end of his corporate career, with a lifelong love for American culture and 40 years of inside experience with the Toyota Way. During the next five years, Anderson and Yoshino spent countless hours learning from each other, reflecting on the past, and envisioning the future. The resulting book - written by Anderson and focused on the profound lessons offered by her mentor Yoshino -- is a beautiful, one-of-a-kind tapestry. Much like the weaving of fabric -- where the beginning work is but a glimpse of the final pattern -- this book was created from many layers of intertwined conversations and reflections. If you've ever been mentored -- in business or in life -- by someone whose words, experiences, and perspectives changed you for the better, you know that an entire book of such selfless generosity and deep wisdom could change the world. For today's business professionals -- dedicated to continuous learning and people-centered leadership -- this is that book. Learning to Lead, Leading to Learn is a leadership book that defies generational or cultural divides, offering a refreshing, proven perspective for all those who dare to lead. The Best Leaders Never Lose the Humility for Learning Learning to Lead, Leading to Learn is much more than a collection of Isao Yoshino's personal stories and insights. It's a memorable, entertaining, and poignant way to highlight important leadership lessons, to record pivotal moments in Toyota's history, and to create something to help veteran and aspiring leaders reflect and learn about themselves. Yoshino's experiences help us understand how Toyota intentionally developed the culture of excellence for which it is renowned today, and how one person "learned to lead" so that he could lead with an intention to learn ... every day and in every way. "The only secret to Toyota is its attitude toward learning." -- Isao Yoshino Let the Past Inform the Future: The Role of Reflection in Leadership By looking back at the past, we can learn and therefore shape our future. Through each story in this unique and inspiring book, Anderson shares Yoshino's experiences with leadership and learning, and his efforts at self-improvement while empowering others. Through those stories, you'll hear his reflections on what he learned then ... and what he is re-learning now with a different perspective as he looks back at the totality of his career. A must-read for those who: -- Want to become more people-centered leaders -- Currently practice lean or continuous improvement methods -- Serve in leadership, coaching, or operational management roles -- Want to learn more about Toyota's history and culture -- Are inspired by heartwarming stories of personal discovery and leadership With a foreword by John Shook, Chairman of the Lean Global Network.




Learning How to Learn


Book Description

A surprisingly simple way for students to master any subject--based on one of the world's most popular online courses and the bestselling book A Mind for Numbers A Mind for Numbers and its wildly popular online companion course "Learning How to Learn" have empowered more than two million learners of all ages from around the world to master subjects that they once struggled with. Fans often wish they'd discovered these learning strategies earlier and ask how they can help their kids master these skills as well. Now in this new book for kids and teens, the authors reveal how to make the most of time spent studying. We all have the tools to learn what might not seem to come naturally to us at first--the secret is to understand how the brain works so we can unlock its power. This book explains: Why sometimes letting your mind wander is an important part of the learning process How to avoid "rut think" in order to think outside the box Why having a poor memory can be a good thing The value of metaphors in developing understanding A simple, yet powerful, way to stop procrastinating Filled with illustrations, application questions, and exercises, this book makes learning easy and fun.




An Introduction to Statistical Learning


Book Description

An Introduction to Statistical Learning provides an accessible overview of the field of statistical learning, an essential toolset for making sense of the vast and complex data sets that have emerged in fields ranging from biology to finance, marketing, and astrophysics in the past twenty years. This book presents some of the most important modeling and prediction techniques, along with relevant applications. Topics include linear regression, classification, resampling methods, shrinkage approaches, tree-based methods, support vector machines, clustering, deep learning, survival analysis, multiple testing, and more. Color graphics and real-world examples are used to illustrate the methods presented. This book is targeted at statisticians and non-statisticians alike, who wish to use cutting-edge statistical learning techniques to analyze their data. Four of the authors co-wrote An Introduction to Statistical Learning, With Applications in R (ISLR), which has become a mainstay of undergraduate and graduate classrooms worldwide, as well as an important reference book for data scientists. One of the keys to its success was that each chapter contains a tutorial on implementing the analyses and methods presented in the R scientific computing environment. However, in recent years Python has become a popular language for data science, and there has been increasing demand for a Python-based alternative to ISLR. Hence, this book (ISLP) covers the same materials as ISLR but with labs implemented in Python. These labs will be useful both for Python novices, as well as experienced users.




Linking Learning and Performance


Book Description

This book provides a step-by-step approach for developing learning and performance measures and a method for analyzing and reporting results. The easy to use format serves as a quick reference—featuring the necessary checklists to evaluate the situation and tools for immediate application in a number of organizational settings—sales, leadership, and technical. It will prove an invaluable resource for anyone involved in training, HRD, human resource measurement and evaluation, and performance improvement.




Linked Courses for General Education and Integrative Learning


Book Description

Research indicates that of the pedagogies recognized as “high impact”, learning communities – one approach to which, the linked course, is the subject of this book – lead to an increased level of student engagement in the freshman year that persists through the senior year, and improve retention. This book focuses on the learning community model that is the most flexible to implement in terms of scheduling, teacher collaboration, and design: the linked course. The faculty may teach independently or together, coordinating syllabi and assignments so that the classes complement each other, and often these courses are linked around a particular interdisciplinary theme. Creating a cohort that works together for two paired courses motivates students, while the course structure promotes integrative learning as students make connections between disciplines.This volume covers both “linked courses” in which faculty may work to coordinate syllabi and assignments, but teach most of their courses separately, as well as well as “paired courses” in which two or more courses are team taught in an integrated program in which faculty participate as learners as well as teachers. Part One, Linked Course Pedagogies, includes several case studies of specific linked courses, including a study skills course paired with a worldview course; a community college course that challenges students’ compartmentalized thinking; and a paired course whose outcomes can be directly compared to parallel stand-alone coursesPart Two, Linked Course Programs, includes a description of several institutional programs representing a variety of linked course program models. Each chapter includes information about program implementation, staffing logistics and concerns, curriculum development, pedagogical strategies, and faculty development.Part Three, Assessing Linked Courses, highlights the role of assessment in supporting, maintaining, and improving linked course programs by sharing assessment models and describing how faculty and administrators have used particular assessment practices in order to improve their linked course programs.




Deep Learning for Coders with fastai and PyTorch


Book Description

Deep learning is often viewed as the exclusive domain of math PhDs and big tech companies. But as this hands-on guide demonstrates, programmers comfortable with Python can achieve impressive results in deep learning with little math background, small amounts of data, and minimal code. How? With fastai, the first library to provide a consistent interface to the most frequently used deep learning applications. Authors Jeremy Howard and Sylvain Gugger, the creators of fastai, show you how to train a model on a wide range of tasks using fastai and PyTorch. You’ll also dive progressively further into deep learning theory to gain a complete understanding of the algorithms behind the scenes. Train models in computer vision, natural language processing, tabular data, and collaborative filtering Learn the latest deep learning techniques that matter most in practice Improve accuracy, speed, and reliability by understanding how deep learning models work Discover how to turn your models into web applications Implement deep learning algorithms from scratch Consider the ethical implications of your work Gain insight from the foreword by PyTorch cofounder, Soumith Chintala




Hanging Out, Messing Around, and Geeking Out


Book Description

An examination of young people's everyday new media practices—including video-game playing, text-messaging, digital media production, and social media use. Conventional wisdom about young people's use of digital technology often equates generational identity with technology identity: today's teens seem constantly plugged in to video games, social networking sites, and text messaging. Yet there is little actual research that investigates the intricate dynamics of youths' social and recreational use of digital media. Hanging Out, Messing Around, and Geeking Out fills this gap, reporting on an ambitious three-year ethnographic investigation into how young people are living and learning with new media in varied settings—at home, in after-school programs, and in online spaces. Integrating twenty-three case studies—which include Harry Potter podcasting, video-game playing, music sharing, and online romantic breakups—in a unique collaborative authorship style, Hanging Out, Messing Around, and Geeking Out is distinctive for its combination of in-depth description of specific group dynamics with conceptual analysis.




UDL and Blended Learning


Book Description

You can develop the skills to meet the needs of learners in any learning environment. This approachable, in-depth guide unites the adaptability of Universal Design for Learning with the flexibility of blended learning, equipping educators with the tools they need to create relevant, authentic, and meaningful learning pathways to meet students where they're at, no matter the time and place or their pace and path. With step-by-step guidance and clear strategies, authors Katie Novak and Catlin Tucker empower teachers to implement these frameworks in the classroom, with a focus on cultivating community, building equity, and increasing accessibility for all learners. As we face increasing uncertainty and frequent disruption to traditional ways of living and learning, UDL and Blended Learning offers bold, innovative, inclusive solutions for navigating a range of learning landscapes, from the home to the classroom and all points in between, no matter what obstacles may lie ahead.