Centre dedocumentation
scientifique

Automated machine learning / Frank Hutter (2019)  

Public contenu dans Directory of Open Access Books DOAB / Directory of Open Access Books DOAB   Titre : Automated machine learning : methods, systems, challenges Type de document : Monographie Auteurs : Frank Hutter, Editeur scientifique ; Lars Kotthoff, Editeur scientifique ; Joaquin Vanschoren, Editeur scientifique Editeur : Springer Nature Année de publication : 2019 Collection : The Springer Series on Challenges in Machine Learning SSCML, ISSN 2520-1328 Importance : 219 p. ISBN/ISSN/EAN : 978-3-030-05318-5 Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Intelligence artificielle [Termes descripteurs IGN] algorithme d'apprentissage [Termes descripteurs IGN] apprentissage automatique [Termes descripteurs IGN] apprentissage profond [Termes descripteurs IGN] optimisation (mathématiques) Index. décimale : 26.40 Intelligence artificielle Résumé : (Editeur) This open access book presents the first comprehensive overview of general methods in Automated Machine Learning (AutoML), collects descriptions of existing systems based on these methods, and discusses the first series of international challenges of AutoML systems. The recent success of commercial ML applications and the rapid growth of the field has created a high demand for off-the-shelf ML methods that can be used easily and without expert knowledge. However, many of the recent machine learning successes crucially rely on human experts, who manually select appropriate ML architectures (deep learning architectures or more traditional ML workflows) and their hyperparameters. To overcome this problem, the field of AutoML targets a progressive automation of machine learning, based on principles from optimization and machine learning itself. This book serves as a point of entry into this quickly-developing field for researchers and advanced students alike, as well as providing a reference for practitioners aiming to use AutoML in their work. Note de contenu : AUTOML METHODS - Hyperparameter Optimization - Meta-Learning - Neural Architecture Search AUTOML SYSTEMS - Auto-WEKA: Automatic Model Selection and Hyperparameter Optimization in WEKA - Hyperopt-Sklearn - Auto-sklearn: Efficient and Robust Automated Machine Learning - Towards Automatically-Tuned Deep Neural Networks - TPOT: A Tree-Based Pipeline Optimization Tool for Automating Machine Learning - The Automatic Statistician AUTOML CHALLENGES - Analysis of the AutoML Challenge Series 2015–2018 - Correction to: Neural Architecture Search Numéro de notice : 26299 Thématique : INFORMATIQUE/MATHEMATIQUE Nature : Monographie DOI : 10.1007%2F978-3-030-05318-5 date de publication en ligne : 04/02/2020 En ligne : https://link.springer.com/book/10.1007%2F978-3-030-05318-5 Format de la ressource électronique : URL Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=95032

Excel data analysis / Hector Guerrero (2019)  

Public Titre : Excel data analysis : modeling and simulation Type de document : Guide/Manuel Auteurs : Hector Guerrero, Auteur Mention d'édition : 2ème édition Editeur : Springer Nature Année de publication : 2019 Importance : 358 p. ISBN/ISSN/EAN : 978-3-030-01279-3 Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Statistiques [Termes descripteurs IGN] analyse de données [Termes descripteurs IGN] données qualitatives [Termes descripteurs IGN] Excel (logiciel) [Termes descripteurs IGN] inférence statistique [Termes descripteurs IGN] méthode de Monte-Carlo [Termes descripteurs IGN] programmation linéaire Résumé : (Editeur) This book offers a comprehensive and readable introduction to modern business and data analytics. It is based on the use of Excel, a tool that virtually all students and professionals have access to. The explanations are focused on understanding the techniques and their proper application, and are supplemented by a wealth of in-chapter and end-of-chapter exercises. In addition to the general statistical methods, the book also includes Monte Carlo simulation and optimization. The second edition has been thoroughly revised: new topics, exercises and examples have been added, and the readability has been further improved. The book is primarily intended for students in business, economics and government, as well as professionals, who need a more rigorous introduction to business and data analytics – yet also need to learn the topic quickly and without overly academic explanations. Note de contenu : 1. Introduction to Spreadsheet Modeling 2. Presentation of Quantitative Data: Data Visualization 3. Analysis of Quantitative Data 4. Presentation of Qualitative Data—Data Visualization 5. Analysis of Qualitative Data 6. Inferential Statistical Analysis of Data 7. Modeling and Simulation: Part 1 8. Modeling and Simulation: Part 2 9. Solver, Scenarios, and Goal Seek Tools Numéro de notice : 26280 Thématique : INFORMATIQUE/MATHEMATIQUE Nature : Manuel informatique DOI : 10.1007/978-3-030-01279-3 En ligne : https://doi.org/10.1007/978-3-030-01279-3 Format de la ressource électronique : URL Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=94931

Java in two semesters / Quentin Charatan (2019)  

Public Titre : Java in two semesters Type de document : Guide/Manuel Auteurs : Quentin Charatan, Auteur ; Aaron Kans, Auteur Editeur : Springer Nature Année de publication : 2019 Importance : 716 p. Format : 16 x 24 cm ISBN/ISSN/EAN : 978-3-319-99420-8 Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Langages informatiques [Termes descripteurs IGN] itération [Termes descripteurs IGN] Java (langage de programmation) [Termes descripteurs IGN] langage de programmation [Termes descripteurs IGN] programmation adaptée à l'objet Résumé : (éditeur) This easy-to-follow textbook teaches Java programming from first principles, as well as covering design and testing methodologies. The text is divided into two parts. Each part supports a one-semester module, the first part addressing fundamental programming concepts, and the second part building on this foundation, teaching the skills required to develop more advanced applications.This fully updated and greatly enhanced fourth edition covers the key developments introduced in Java 8, including material on JavaFX, lambda expressions and the Stream API.Topics and features: begins by introducing fundamental programming concepts such as declaration of variables, control structures, methods and arrays; goes on to cover the fundamental object-oriented concepts of classes and objects, inheritance and polymorphism; uses JavaFX throughout for constructing event-driven graphical interfaces; includes advanced topics such as interfaces and lambda expressions, generics, collection classes and exceptions; explains file-handling techniques, packages, multi-threaded programs, socket programming, remote database access and processing collections using streams; includes self-test questions and programming exercises at the end of each chapter, as well as two illuminating case studies; provides additional resources at its associated website (simply go to springer.com and search for 'Java in Two Semesters'), including a guide on how to install and use the NetBeans™ Java IDE.Offering a gentle introduction to the field, assuming no prior knowledge of the subject, Java in Two Semesters is the ideal companion to undergraduate modules in software development or programming. Note de contenu : Part I 1- The First Step 2- Building Blocks 3- Selection 4- Iteration 5- Methods 6- Arrays 7- Classes and Objects 8- Implementing Classes 9- Inheritance 10- Introducing JavaFX 11- Case Study—Part 1 12- Case Study—Part 2 Part II Semester Two 13- Interfaces and Lambda Expressions 14- Exceptions 15- The Java Collections Framework 16- Advanced JavaFX 17- JavaFX: Interacting with the User 18- Working with Files 19- Packages 20- Multi-threaded Programs 21- Advanced Case Study 22- The Stream API 23- Working with Sockets 24- Java in Context Numéro de notice : 25810 Thématique : INFORMATIQUE Nature : Manuel informatique En ligne : https://doi.org/10.1007/978-3-319-99420-8 Format de la ressource électronique : URL Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=95070

Fundamentals of Java programming / Mitsunori Ogihara (2018)  

Public Titre : Fundamentals of Java programming Type de document : Guide/Manuel Auteurs : Mitsunori Ogihara, Auteur Editeur : Springer Nature Année de publication : 2018 Importance : 515 p. Format : 18 x 26 cm ISBN/ISSN/EAN : 978-3-319-89491-1 Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Langages informatiques [Termes descripteurs IGN] Java (langage de programmation) [Termes descripteurs IGN] programmation informatique Résumé : (éditeur) Making extensive use of examples, this textbook on Java programming teaches the fundamental skills for getting started in a command-line environment. Meant to be used for a one-semester course to build solid foundations in Java, Fundamentals of Java Programming eschews second-semester content to concentrate on over 180 code examples and 250 exercises. Key object classes (String, Scanner, PrintStream, Arrays, and File) are included to get started in Java programming. The programs are explained with almost line-by-line descriptions, also with chapter-by-chapter coding exercises. Teaching resources include solutions to the exercises, as well as digital lecture slides Note de contenu : I- Programming Basics II- Loops III- Arrays and Objects IV- Advanced Concepts Numéro de notice : 25807 Thématique : INFORMATIQUE Nature : Manuel informatique DOI : 10.1007/978-3-319-89491-1 En ligne : https://doi.org/10.1007/978-3-319-89491-1 Format de la ressource électronique : URL Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=95063

Introduction to Deep Learning / Sandro Skansi (2018)  

Public Titre : Introduction to Deep Learning : From Logical Calculus to Artificial Intelligence Type de document : Monographie Auteurs : Sandro Skansi, Auteur Editeur : Springer Nature Année de publication : 2018 Importance : 196 p. Format : 16 x 24 cm ISBN/ISSN/EAN : 978-3-319-73004-2 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Intelligence artificielle [Termes descripteurs IGN] apprentissage profond [Termes descripteurs IGN] classification [Termes descripteurs IGN] codage [Termes descripteurs IGN] estimation par noyau [Termes descripteurs IGN] matrice de covariance [Termes descripteurs IGN] Perceptron multicouche [Termes descripteurs IGN] Python (langage de programmation) [Termes descripteurs IGN] régression logistique [Termes descripteurs IGN] réseau neuronal artificiel [Termes descripteurs IGN] réseau neuronal convolutif [Termes descripteurs IGN] sciences cognitives [Termes descripteurs IGN] théorie des probabilités Résumé : (auteur) This textbook presents a concise, accessible and engaging first introduction to deep learning, offering a wide range of connectionist models which represent the current state-of-the-art. The text explores the most popular algorithms and architectures in a simple and intuitive style, explaining the mathematical derivations in a step-by-step manner. The content coverage includes convolutional networks, LSTMs, Word2vec, RBMs, DBNs, neural Turing machines, memory networks and autoencoders. Numerous examples in working Python code are provided throughout the book, and the code is also supplied separately at an accompanying website. Topics and features: Introduces the fundamentals of machine learning, and the mathematical and computational prerequisites for deep learning Discusses feed-forward neural networks, and explores the modifications to these which can be applied to any neural network Examines convolutional neural networks, and the recurrent connections to a feed-forward neural network Describes the notion of distributed representations, the concept of the autoencoder, and the ideas behind language processing with deep learning Presents a brief history of artificial intelligence and neural networks, and reviews interesting open research problems in deep learning and connectionism This clearly written and lively primer on deep learning is essential reading for graduate and advanced undergraduate students of computer science, cognitive science and mathematics, as well as fields such as linguistics, logic, philosophy, and psychology. Note de contenu : 1- From Logic to Cognitive Science 2- Mathematical and Computational Prerequisites 3- Machine Learning Basics 4- Feedforward Neural Networks 5- Modifications and Extensions to a Feed-Forward Neural Network 6- Convolutional Neural Networks 7- Recurrent Neural Networks 8- Autoencoders 9- Neural Language Models 10- An Overview of Different Neural Network Architectures 11- Conclusion Numéro de notice : 25787 Thématique : INFORMATIQUE/MATHEMATIQUE Nature : Monographie En ligne : https://doi.org/10.1007/978-3-319-73004-2 Format de la ressource électronique : URL Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=94990

Physics of oscillations and waves / Arnt Inge Vistnes (2018)  

Permalink

Open Geospatial Data, Software and Standards (2016 - )  

Permalink

Photogrammetric computer vision / Wolfgang Förstner (2016)

Permalink

Carbon Balance and Management  

Permalink