{"product_id":"systems-engineering-neural-networks-isbn-9781119901990","title":"Systems Engineering Neural Networks","description":"\u003cb\u003eSYSTEMS ENGINEERING NEURAL NETWORKS\u003c\/b\u003e \u003cp\u003e\u003cb\u003eA complete and authoritative discussion of systems engineering and neural networks\u003c\/b\u003e \u003c\/p\u003e\u003cp\u003eIn \u003ci\u003eSystems Engineering Neural Networks\u003c\/i\u003e, a team of distinguished researchers deliver a thorough exploration of the fundamental concepts underpinning the creation and improvement of neural networks with a systems engineering mindset. In the book, you’ll find a general theoretical discussion of both systems engineering and neural networks accompanied by coverage of relevant and specific topics, from deep learning fundamentals to sport business applications. \u003c\/p\u003e\u003cp\u003eReaders will discover in-depth examples derived from many years of engineering experience, a comprehensive glossary with links to further reading, and supplementary online content. The authors have also included a variety of applications programmed in both Python 3 and Microsoft Excel. \u003c\/p\u003e\u003cp\u003eThe book provides: \u003c\/p\u003e\u003cul\u003e\n\u003cli\u003e A thorough introduction to neural networks, introduced as key element of complex systems\u003c\/li\u003e \u003cli\u003e Practical discussions of systems engineering and forecasting, complexity theory and optimization and how these techniques can be used to support applications outside of the traditional AI domains\u003c\/li\u003e \u003cli\u003e Comprehensive explorations of input and output, hidden layers, and bias in neural networks, as well as activation functions, cost functions, and back-propagation\u003c\/li\u003e \u003cli\u003e Guidelines for software development incorporating neural networks with a systems engineering methodology\u003c\/li\u003e\n\u003c\/ul\u003e \u003cp\u003ePerfect for students and professionals eager to incorporate machine learning techniques into their products and processes, \u003ci\u003eSystems Engineering Neural Networks \u003c\/i\u003ewill also earn a place in the libraries of managers and researchers working in areas involving neural networks. \u003c\/p\u003e\u003cp\u003eABOUT THE AUTHORS\u003c\/p\u003e \u003cp\u003eACKNOWLEDGEMENTS 7\u003c\/p\u003e \u003cp\u003eHOW TO READ THIS BOOK 8\u003c\/p\u003e \u003cp\u003ePart I 9\u003c\/p\u003e \u003cp\u003e 1 A BRIEF INTRODUCTION 9\u003c\/p\u003e \u003cp\u003eTHE SYSTEMS ENGINEERING APPROACH TO ARTIFICIAL INTELLIGENCE (AI) 14\u003c\/p\u003e \u003cp\u003eSOURCES 18\u003c\/p\u003e \u003cp\u003eCHAPTER SUMMARY 18\u003c\/p\u003e \u003cp\u003eQUESTIONS 19\u003c\/p\u003e \u003cp\u003e2 DEFINING A NEURAL NETWORK 20\u003c\/p\u003e \u003cp\u003eBIOLOGICAL NETWORKS 22\u003c\/p\u003e \u003cp\u003eFROM BIOLOGY TO MATHEMATICS 24\u003c\/p\u003e \u003cp\u003eWE CAME A FULL CIRCLE 25\u003c\/p\u003e \u003cp\u003eTHE MODEL OF McCULLOCH-PITTS 25\u003c\/p\u003e \u003cp\u003eTHE ARTIFICIAL NEURON OF ROSENBLATT 26\u003c\/p\u003e \u003cp\u003eFINAL REMARKS 33\u003c\/p\u003e \u003cp\u003eSOURCES 35\u003c\/p\u003e \u003cp\u003eCHAPTER SUMMARY 36\u003c\/p\u003e \u003cp\u003eQUESTIONS 37\u003c\/p\u003e \u003cp\u003e3 ENGINEERING NEURAL NETWORKS 38\u003c\/p\u003e \u003cp\u003eA BRIEF RECAP ON SYSTEMS ENGINEERING 40\u003c\/p\u003e \u003cp\u003eTHE KEYSTONE: SE4AI AND AI4SE 41\u003c\/p\u003e \u003cp\u003eENGINEERING COMPLEXITY 41\u003c\/p\u003e \u003cp\u003eTHE SPORT SYSTEM 45\u003c\/p\u003e \u003cp\u003eENGINEERING A SPORT CLUB 51\u003c\/p\u003e \u003cp\u003eOPTIMISATION 52\u003c\/p\u003e \u003cp\u003eAN EXAMPLE OF DECISION MAKING 56\u003c\/p\u003e \u003cp\u003eFUTURISM AND FORESIGHT 60\u003c\/p\u003e \u003cp\u003eQUALITATIVE TO QUANTITATIVE 61\u003c\/p\u003e \u003cp\u003eFUZZY THINKING 64\u003c\/p\u003e \u003cp\u003eIT IS ALL IN THE TOOLS 74\u003c\/p\u003e \u003cp\u003eSOURCES 77\u003c\/p\u003e \u003cp\u003eCHAPTER SUMMARY 77\u003c\/p\u003e \u003cp\u003eQUESTIONS 78\u003c\/p\u003e \u003cp\u003ePart II 79\u003c\/p\u003e \u003cp\u003e4 SYSTEMS THINKING FOR SOFTWARE DEVELOPMENT 79\u003c\/p\u003e \u003cp\u003ePROGRAMMING LANGUAGES 82\u003c\/p\u003e \u003cp\u003eONE MORE THING: SOFTWARE ENGINEERING 94\u003c\/p\u003e \u003cp\u003eCHAPTER SUMMARY 101\u003c\/p\u003e \u003cp\u003eQUESTIONS 102\u003c\/p\u003e \u003cp\u003eSOURCES 102\u003c\/p\u003e \u003cp\u003e5 PRACTICE MAKES PERFECT 103\u003c\/p\u003e \u003cp\u003eEXAMPLE 1: COSINE FUNCTION 105\u003c\/p\u003e \u003cp\u003eEXAMPLE 2: CORROSION ON A METAL STRUCTURE 112\u003c\/p\u003e \u003cp\u003eEXAMPLE 3: DEFINING ROLES OF ATHLETES 127\u003c\/p\u003e \u003cp\u003eEXAMPLE 4: ATHLETE’S PERFORMANCE 134\u003c\/p\u003e \u003cp\u003eEXAMPLE 5: TEAM PERFORMANCE 142\u003c\/p\u003e \u003cp\u003eA human-defined-system 142\u003c\/p\u003e \u003cp\u003eHuman Factors 143\u003c\/p\u003e \u003cp\u003eThe sport team as system of interest 144\u003c\/p\u003e \u003cp\u003eImpact of Human Error on Sports Team Performance 145\u003c\/p\u003e \u003cp\u003eEXAMPLE 6: TREND PREDICTION 156\u003c\/p\u003e \u003cp\u003eEXAMPLE 7: SYMPLEX AND GAME THEORY 163\u003c\/p\u003e \u003cp\u003eEXAMPLE 8: SORTING MACHINE FOR LEGO® BRICKS 168\u003c\/p\u003e \u003cp\u003ePart III 174\u003c\/p\u003e \u003cp\u003e6 INPUT\/OUTPUT, HIDDEN LAYER AND BIAS 174\u003c\/p\u003e \u003cp\u003eINPUT\/OUTPUT 175\u003c\/p\u003e \u003cp\u003eHIDDEN LAYER 180\u003c\/p\u003e \u003cp\u003eBIAS 184\u003c\/p\u003e \u003cp\u003eFINAL REMARKS 186\u003c\/p\u003e \u003cp\u003eCHAPTER SUMMARY 187\u003c\/p\u003e \u003cp\u003eQUESTIONS 188\u003c\/p\u003e \u003cp\u003e7 ACTIVATION FUNCTION 189\u003c\/p\u003e \u003cp\u003eTYPES OF ACTIVATION FUNCTIONS 191\u003c\/p\u003e \u003cp\u003eACTIVATION FUNCTION DERIVATIVES 194\u003c\/p\u003e \u003cp\u003eACTIVATION FUNCTIONS RESPONSE TO W AND b VARIABLES 200\u003c\/p\u003e \u003cp\u003eFINAL REMARKS 202\u003c\/p\u003e \u003cp\u003eCHAPTER SUMMARY 204\u003c\/p\u003e \u003cp\u003eQUESTIONS 205\u003c\/p\u003e \u003cp\u003eSOURCES 205\u003c\/p\u003e \u003cp\u003e8 COST FUNCTION, BACK-PROPAGATION AND OTHER ITERATIVE METHODS 206\u003c\/p\u003e \u003cp\u003eWHAT IS THE DIFFERENCE BETWEEN LOSS AND COST? 209\u003c\/p\u003e \u003cp\u003eTRAINING THE NEURAL NETWORK 212\u003c\/p\u003e \u003cp\u003eBACK-PROPAGATION (BP) 214\u003c\/p\u003e \u003cp\u003eONE MORE THING: GRADIENT METHOD AND CONJUGATE GRADIENT METHOD 218\u003c\/p\u003e \u003cp\u003eONE MORE THING: NEWTON’S METHOD 221\u003c\/p\u003e \u003cp\u003eCHAPTER SUMMARY 223\u003c\/p\u003e \u003cp\u003eQUESTIONS 224\u003c\/p\u003e \u003cp\u003eSOURCES 224\u003c\/p\u003e \u003cp\u003e 9 CONCLUSIONS AND FUTURE DEVELOPMENTS 225\u003c\/p\u003e \u003cp\u003eGLOSSARY AND INSIGHTS 233\u003c\/p\u003e  \u003cp\u003e\u003cb\u003eAlessandro Migliaccio\u003c\/b\u003e is a certified systems engineer and member of the INCOSE Artificial Intelligence Working Group. He is a graduate of the Delft University of Technology in Space Engineering, USA, and has second level master’s degree in Robotics and Intelligent Systems. \u003c\/p\u003e\u003cp\u003e\u003cb\u003eGiovanni Iannone\u003c\/b\u003e is a mechanical engineer and a graduate of the University of Naples Federico II. Second level master’s degree in Systems Engineering at Missouri University of Science and Technology, USA. He has been an active member of INCOSE for several years.   \u003c\/p\u003e\u003cp\u003e\u003cb\u003eA complete and authoritative discussion of systems engineering and neural networks\u003c\/b\u003e \u003c\/p\u003e\u003cp\u003eIn \u003ci\u003eSystems Engineering Neural Networks\u003c\/i\u003e, a team of distinguished researchers deliver a thorough exploration of the fundamental concepts underpinning the creation and improvement of neural networks with a systems engineering mindset. In the book, you’ll find a general theoretical discussion of both systems engineering and neural networks accompanied by coverage of relevant and specific topics, from deep learning fundamentals to sport business applications. \u003c\/p\u003e\u003cp\u003eReaders will discover in-depth examples derived from many years of engineering experience, a comprehensive glossary with links to further reading, and supplementary online content. The authors have also included a variety of applications programmed in both Python 3 and Microsoft Excel. \u003c\/p\u003e\u003cp\u003eThe book provides: \u003c\/p\u003e\u003cul\u003e\n\u003cli\u003e A thorough introduction to neural networks, introduced as key element of complex systems\u003c\/li\u003e \u003cli\u003e Practical discussions of systems engineering and forecasting, complexity theory and optimization and how these techniques can be used to support applications outside of the traditional AI domains\u003c\/li\u003e \u003cli\u003e Comprehensive explorations of input and output, hidden layers, and bias in neural networks, as well as activation functions, cost functions, and back-propagation\u003c\/li\u003e \u003cli\u003e Guidelines for software development incorporating neural networks with a systems engineering methodology\u003c\/li\u003e\n\u003c\/ul\u003e \u003cp\u003ePerfect for students and professionals eager to incorporate machine learning techniques into their products and processes, \u003ci\u003eSystems Engineering Neural Networks \u003c\/i\u003ewill also earn a place in the libraries of managers and researchers working in areas involving neural networks.\u003c\/p\u003e","brand":"Wiley","offers":[{"title":"Default Title","offer_id":47990126215397,"sku":"NP9781119901990","price":130.0,"currency_code":"USD","in_stock":false}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/1842\/7735\/files\/9781119901990.jpg?v=1761786614","url":"https:\/\/k12savings.com\/es\/products\/systems-engineering-neural-networks-isbn-9781119901990","provider":"K12savings","version":"1.0","type":"link"}