LEADER 04310nam 2200565I 450 001 9910966807603321 005 20230124202106.0 010 $a9781838825720 010 $a183882572X 035 $a(CKB)4920000000457578 035 $a(OCoLC)1181958606 035 $a(OCoLC)on1181958606 035 $a(MiAaPQ)EBC6126530 035 $a(PPN)243777736 035 $a(FR-PaCSA)88882283 035 $a(CaSebORM)9781838821654 035 $a(DE-B1597)695085 035 $a(DE-B1597)9781838825720 035 $a(FRCYB88882283)88882283 035 $a(EXLCZ)994920000000457578 100 $a20200803d2020 uy 0 101 0 $aeng 135 $aurunu|||||||| 181 $ctxt$2rdacontent 182 $cc$2rdamedia 183 $acr$2rdacarrier 200 10$aAdvanced deep learning with TensorFlow 2 and Keras $eapply DL, GANs, VAEs, deep RL, unsupervised learning, object detection and segmentation, and more /$fRowel Atienza 205 $aSecond edition. 210 1$aBirmingham, UK :$cPackt Publishing,$d2020. 215 $a1 online resource (1 volume) $cillustrations 311 08$a9781838821654 311 08$a1838821651 320 $aIncludes bibliographical references and index. 330 $aUpdated and revised second edition of the bestselling guide to advanced deep learning with TensorFlow 2 and Keras Key Features Explore the most advanced deep learning techniques that drive modern AI results New coverage of unsupervised deep learning using mutual information, object detection, and semantic segmentation Completely updated for TensorFlow 2.x Book Description Advanced Deep Learning with TensorFlow 2 and Keras, Second Edition is a completely updated edition of the bestselling guide to the advanced deep learning techniques available today. Revised for TensorFlow 2.x, this edition introduces you to the practical side of deep learning with new chapters on unsupervised learning using mutual information, object detection (SSD), and semantic segmentation (FCN and PSPNet), further allowing you to create your own cutting-edge AI projects. Using Keras as an open-source deep learning library, the book features hands-on projects that show you how to create more effective AI with the most up-to-date techniques. Starting with an overview of multi-layer perceptrons (MLPs), convolutional neural networks (CNNs), and recurrent neural networks (RNNs), the book then introduces more cutting-edge techniques as you explore deep neural network architectures, including ResNet and DenseNet, and how to create autoencoders. You will then learn about GANs, and how they can unlock new levels of AI performance. Next, you'll discover how a variational autoencoder (VAE) is implemented, and how GANs and VAEs have the generative power to synthesize data that can be extremely convincing to humans. You'll also learn to implement DRL such as Deep Q-Learning and Policy Gradient Methods, which are critical to many modern results in AI. What you will learn Use mutual information maximization techniques to perform unsupervised learning Use segmentation to identify the pixel-wise class of each object in an image Identify both the bounding box and class of objects in an image using object detection Learn the building blocks for advanced techniques - MLPss, CNN, and RNNs Understand deep neural networks - including ResNet and DenseNet Understand and build autoregressive models ? autoencoders, VAEs, and GANs Discover and implement deep reinforcement learning methods Who this book is for This is not an introductory book, so fluency with Python is required. The reader should also be familiar with some machine learning approaches, and practical experience with DL will also be hel... 606 $aArtificial intelligence 606 $aMachine learning 606 $aPython (Computer program language) 606 $aNeural networks (Computer science) 615 0$aArtificial intelligence. 615 0$aMachine learning. 615 0$aPython (Computer program language) 615 0$aNeural networks (Computer science) 676 $a005.133 700 $aAtienza$b Rowel$01691143 801 0$bUMI 801 1$bUMI 906 $aBOOK 912 $a9910966807603321 996 $aAdvanced deep learning with TensorFlow 2 and Keras$94340037 997 $aUNINA LEADER 06045nam 22005775 450 001 9910299356503321 005 20200910205431.0 010 $a3-319-95504-7 024 7 $a10.1007/978-3-319-95504-9 035 $a(CKB)4100000007142733 035 $a(MiAaPQ)EBC5598687 035 $a(DE-He213)978-3-319-95504-9 035 $a(PPN)232473455 035 $a(EXLCZ)994100000007142733 100 $a20181113d2018 u| 0 101 0 $aeng 135 $aurcnu|||||||| 181 $ctxt$2rdacontent 182 $cc$2rdamedia 183 $acr$2rdacarrier 200 10$aHandbook of Dynamic Data Driven Applications Systems /$fedited by Erik Blasch, Sai Ravela, Alex Aved 205 $a1st ed. 2018. 210 1$aCham :$cSpringer International Publishing :$cImprint: Springer,$d2018. 215 $a1 online resource (734 pages) 311 $a3-319-95503-9 327 $a1 Introduction to Dynamic Data Driven Applications Systems -- 2 Tractable Non-Gaussian Representation in Dynamic Data Driven Coherent Fluid Mapping -- 3 Dynamic Data-Driven Adaptive Observations in Data Assimilation for Multi-scale Systems -- 4 Dynamic Data-Driven Uncertainty Quantification via Polynomial Chaos for Space Situational Awareness -- 5 Towards Learning Spatio-Temporal Data Stream Relationships for Failure Detection in Avionics -- 6 Markov Modeling of Time Series via Spectral Analysis for Detection of Combustion Instabilities -- 7 Dynamic Space-Time Model for Syndromic Surveillance with Particle Filters and Dirichlet Process -- 8 A Computational Steering Framework for Large-Scale Composite Structures -- 9 Development of Intelligent and Predictive Self-Healing Composite Structures using Dynamic Data-Driven Applications Systems -- 10 Dynamic Data-Driven Approach for Unmanned Aircraft Systems aero-elastic response analysis -- 11 Transforming Wildfire Detection and Prediction using New and Underused Sensor and Data Sources Integrated with Modeling -- 12 Dynamic Data Driven Application Systems for Identification of Biomarkers in DNA Methylation -- 13 Photometric Steropsis for 3D Reconstruction of Space Objects -- 14 Aided Optimal Search: Data-Driven Target Pursuit from On-Demand Delayed Binary Observations -- 15 Optimization of Multi-Target Tracking within a Sensor Network via Information Guided Clustering -- 16 Data-Driven Prediction of Confidence for EVAR in Time-varying Datasets -- 17 DDDAS for Attack Detection and Isolation of Control Systems -- 18 Approximate Local Utility Design for Potential Game Approach to Cooperative Sensor Network Planning -- 19 Dynamic Sensor-Actor Interactions for Path-Planning in a Threat Field -- 20 Energy-Aware Dynamic Data-Driven Distributed Traffic Simulation for Energy and Emissions Reduction -- 21 A Dynamic Data-Driven Optimization Framework for Demand Side Management in Microgrids -- 22 Dynamic Data Driven Partitioning of Smart Grid Using Learning Methods -- 23 Design of a Dynamic Data-Driven System for Multispectral Video Processing -- 24 Light Field Image Compression -- 25 On Compression of Machine-derived Context Sets for Fusion of Multi-model Sensor Data -- 26 Simulation-based Optimization as a Service for Dynamic Data-driven Applications Systems -- 27 Privacy and Security Issues in DDDAS Systems -- 28 Dynamic Data Driven Application Systems (DDDAS) for Multimedia Content Analysis -- 29 Parzen Windows: Simplest Regularization Algorithm -- 30 Multiscale DDDAS Framework for Damage Prediction in Aerospace Composite Structures -- 31 A Dynamic Data-Driven Stochastic State-awareness Framework for the Next Generation of Bio-inspired Fly-by-feel Aerospace Vehicles -- DDDAS: The Way Forward. . 330 $aThe Handbook of Dynamic Driven Applications Systems establishes an authoritative reference of DDDAS, pioneered by Dr. Darema and the co-authors for researchers and practitioners developing DDDAS technologies. Beginning with general concepts and history of the paradigm, the text provides 32 chapters by leading experts in10 application areas to enable an accurate understanding, analysis, and control of complex systems; be they natural, engineered, or societal: Earth and Space Data Assimilation Aircraft Systems Processing Structures Health Monitoring Biological Data Assessment Object and Activity Tracking Embedded Control and Coordination Energy-Aware Optimization Image and Video Computing Security and Policy Coding Systems Design The authors explain how DDDAS unifies the computational and instrumentation aspects of an application system, extends the notion of Smart Computing to span from the high-end to the real-time data acquisition and control, and manages Big Data exploitation with high-dimensional model coordination. 606 $aComputer simulation 606 $aSystem theory 606 $aComputers 606 $aComputers, Special purpose 606 $aSimulation and Modeling$3https://scigraph.springernature.com/ontologies/product-market-codes/I19000 606 $aSystems Theory, Control$3https://scigraph.springernature.com/ontologies/product-market-codes/M13070 606 $aModels and Principles$3https://scigraph.springernature.com/ontologies/product-market-codes/I18016 606 $aSpecial Purpose and Application-Based Systems$3https://scigraph.springernature.com/ontologies/product-market-codes/I13030 615 0$aComputer simulation. 615 0$aSystem theory. 615 0$aComputers. 615 0$aComputers, Special purpose. 615 14$aSimulation and Modeling. 615 24$aSystems Theory, Control. 615 24$aModels and Principles. 615 24$aSpecial Purpose and Application-Based Systems. 676 $a004.21 702 $aBlasch$b Erik$4edt$4http://id.loc.gov/vocabulary/relators/edt 702 $aRavela$b Sai$4edt$4http://id.loc.gov/vocabulary/relators/edt 702 $aAved$b Alex$4edt$4http://id.loc.gov/vocabulary/relators/edt 906 $aBOOK 912 $a9910299356503321 996 $aHandbook of Dynamic Data Driven Applications Systems$92851120 997 $aUNINA