가야대학교 분성도서관
주메뉴
자료검색
- Home
- 상세정보
상세정보
부가기능
The deep learning revolution / [electronic resource]
상세 프로파일
| 자료유형 | E-Book |
|---|---|
| 개인저자 | Sejnowski, Terrence J. (Terrence Joseph), author. |
| 서명/저자사항 | The deep learning revolution /Terrence J. Sejnowski.[electronic resource] |
| 발행사항 | Cambridge, MA : The MIT Press, 2018. |
| 형태사항 | 1 online resource. |
| ISBN | 9780262346825 0262346826 |
| 서지주기 | Includes bibliographical references and index. |
| 내용주기 | Intro; Contents; Preface; I: Intelligence Reimagined; Timeline; 1 The Rise of Machine Learning; Learning How to Drive; Learning How to Translate; Learning How to Listen; Learning How to Diagnose; Learning How to Make Money; Learning the Law; Learning How to Play Poker; Learning How to Play Go; Learning How to Become More Intelligent; The Shifting Job Market; Is Artificial Intelligence an Existential Threat?; Back to the Future; 2 The Rebirth of Artificial Intelligence; Child's Play?; Why Vision Is a Hard Problem; Expert Systems; Into the Lion's Den; 3 The Dawn of Neural Networks Early PioneersLearning from Examples; SEXNET; Perceptrons Eclipsed; 4 Brain-style Computing; How the Brain Works; Early Pioneers; George Boole and Machine Learning; The Humpty Dumpty Project; What I learned at Woods Hole; The Missing Link; 5 Insights from the Visual System; Vision from the Bottom Up; Vision in the Cerebral Cortex; Synapse Plasticity; Shape from Shading; Visual Maps in the Cortex Are Hierarchically Organized; The Birth of Cognitive Neuroscience; II: Many Ways to Learn; Timeline; 6 The Cocktail Party Problem; Independent Component Analysis; Independent Components in the Brain Beyond Independent Component Analysis7 The Hopfield Net and Boltzmann Machine; John Hopfield; A Network with Content-Addressable Memories; Finding the Global Energy Minimum; Boltzmann Machines; Hebbian Synaptic Plasticity; Learning Mirror Symmetries; Learning to Recognize Handwritten Zip Codes; Unsupervised Learning and Cortical Development; 8 Backpropagating Errors; Optimization; NETtalk; Neural Networks Reborn; Understanding Deep Learning; Limitations of Neural Networks; Passages; 9 Convolutional Learning; Steady Progress in Machine Learning; Convolutional Neural Networks Deep Learning Meets the Visual HierarchyWorking Memory and Persistence of Activity; Generative Adversarial Networks; It's All about Scaling; 10 Reward Learning; Learning How to Play Backgammon; Reward Learning in Brains; Motivation and the Basal Ganglia; Learning How to Soar; Learning How to Sing; Other Forms of Learning; What Is Missing?; 11 Neural Information Processing Systems; Deep Learning at the Gaming Table; Preparing for the Future; III: Technological and Scientific Impact; Timeline; 12 The Future of Machine Learning; Life in the Twenty-First Century; The Future of Identity The Rise of Social RobotsRubi; Facial Expressions Are a Window into Your Soul; The Science of Learning; Learning How to Learn; Brain Training; The AI Business; 13 The Age of Algorithms; Complex Systems; Cellular Automata; Is the Brain a Computer?; The Space of Algorithms; 14 Hello, Mr. Chips; Hot Chips; Cool Chips; Neuromorphic Engineering; No More Moore's Law?; 15 Inside Information; Information Theory; Number Theory; Predictive Coding; The Global Brain; Operating Systems; It's Information, All the Way Down; Playing the Long Game; 16 Consciousness; Neural Correlates of Consciousness |
| 요약 | How deep learning-from Google Translate to driverless cars to personal cognitive assistants-is changing our lives and transforming every sector of the economy. The deep learning revolution has brought us driverless cars, the greatly improved Google Translate, fluent conversations with Siri and Alexa, and enormous profits from automated trading on the New York Stock Exchange. Deep learning networks can play poker better than professional poker players and defeat a world champion at Go. In this book, Terry Sejnowski explains how deep learning went from being an arcane academic field to a disruptive technology in the information economy. Sejnowski played an important role in the founding of deep learning, as one of a small group of researchers in the 1980s who challenged the prevailing logic-and-symbol based version of AI. The new version of AI Sejnowski and others developed, which became deep learning, is fueled instead by data. Deep networks learn from data in the same way that babies experience the world, starting with fresh eyes and gradually acquiring the skills needed to navigate novel environments. Learning algorithms extract information from raw data; information can be used to create knowledge; knowledge underlies understanding; understanding leads to wisdom. Someday a driverless car will know the road better than you do and drive with more skill; a deep learning network will diagnose your illness; a personal cognitive assistant will augment your puny human brain. It took nature many millions of years to evolve human intelligence; AI is on a trajectory measured in decades. Sejnowski prepares us for a deep learning future. |
| 일반주제명 | Machine learning. Big data. Artificial intelligence -- Social aspects. Artificial intelligence -- Social aspects. Big data. Machine learning. COMPUTERS / Database Management / Data Mining. COMPUTERS / General |
| 언어 | 영어 |
| 기타형태 저록 | Print version:Sejnowski, Terrence J. (Terrence Joseph).Deep learning revolution.Cambridge, MA : The MIT Press, 20189780262038034 |
| 대출바로가기 | http://search.ebscohost.com/login.aspx?direct=true&scope=site&db=nlebk&db=nlabk&AN=1906666 |
소장정보
- 소장정보
인쇄
| No. | 등록번호 | 청구기호 | 소장처 | 도서상태 | 반납예정일 | 예약 | 서비스 | 매체정보 |
|---|---|---|---|---|---|---|---|---|
| 1 | WE00015202 | 006.3/1 | 가야대학교/전자책서버(컴퓨터서버)/ | 대출가능 |
|
카피라이터
