Listing 1 - 10 of 11 | << page >> |
Sort by
|
Choose an application
machine learning --- python --- Scikit-learn
Choose an application
Cet ouvrage, conçu pour tous ceux qui souhaitent s'initier au Machine Learning (apprentissage automatique) est la traduction de la première partie du best-seller américain Hands-On Machine Learning with Scikit-Learn & TensorFlow. Il ne requiert que peu de connaissances en mathématiques et présente les fondamentaux du Machine Learning d'une façon très pratique à l'aide de Scikit-Learn qui est l'un des frameworks de ML les plus utilisés actuellement. Des exercices corrigés permettent de s'assurer que l'on a assimilé les concepts et que l'on maîtrise les outils. Des compléments en ligne interactifs sous forme de Jupyter notebooks complètent le livre avec des exemples exécutables. Ce premier titre est complété par un second ouvrage intitulé Deep Learning avec TensorFlow.
Machine learning. --- Artificial intelligence. --- Apprentissage automatique. --- Intelligence artificielle. --- Scikit-Learn --- Apprentissage automatique
Choose an application
Eine Reihe technischer Durchbrüche beim Deep Learning haben das gesamte Gebiet des maschinellen Lernens in den letzten Jahren beflügelt. Inzwischen können sogar Programmierer, die kaum etwas über diese Technologie wissen, mit einfachen, effizienten Werkzeugen Machine-Learning-Programme implementieren. Dieses praxisorientierte Buch zeigt Ihnen wie. Mit konkreten Beispielen, einem Minimum an Theorie und zwei unmittelbar anwendbaren Python-Frameworks – Scikit-Learn und TensorFlow 2 – verhilft Ihnen der Autor Aurélien Géron zu einem intuitiven Verständnis der Konzepte und Tools für das Entwickeln intelligenter Systeme. Sie lernen eine Vielzahl von Techniken kennen, beginnend mit einfacher linearer Regression bis hin zu Deep Neural Networks. Die in jedem Kapitel enthaltenen Übungen helfen Ihnen, das Gelernte in die Praxis umzusetzen. Um direkt zu starten, benötigen Sie lediglich etwas Programmiererfahrung.
Python --- Künstliche Intelligenz --- Neuronale Netze --- Algorithmen --- Machine Learning --- KI --- Artificial Intelligence --- Deep Learning --- matplotlib --- NumPy --- Data Science --- Maschinelles Lernen --- scikit-learn --- AI --- Statistische Datenanalyse --- TensorFlow --- Geron
Choose an application
Das praktische Nachschlagewerk zum Machine Learning mit strukturierten Daten
Künstliche Intelligenz --- Algorithmen --- KI --- Neural Networks --- Artificial Intelligence --- NumPy --- Data Science --- Maschinelles Lernen --- überwachtes Lernen --- Pandas --- scikit-learn --- AI --- Statistische Datenanalyse --- Supervised Learning
Choose an application
Long description: Bewährte Praxislösungen für komplexe Machine-Learning-Aufgaben Behandelt alle Phasen der ML-Produktpipeline Klar strukturierter Aufbau: Konzepte und Zusammenhänge erschließen sich dadurch schnell Fokus auf TensorFlow, aber auch übertragbar auf PyTorch-Projekte Die Design Patterns in diesem Buch zeigen praxiserprobte Methoden und Lösungen für wiederkehrende Aufgaben beim Machine Learning. Die Autoren, drei Machine-Learning-Experten bei Google, beschreiben bewährte Herangehensweisen, um Data Scientists und Data Engineers bei der Lösung gängiger Probleme im gesamten ML-Prozess zu unterstützen. Die Patterns bündeln die Erfahrungen von Hunderten von Experten und bieten einfache, zugängliche Best Practices.In diesem Buch finden Sie detaillierte Erläuterungen zu 30 Patterns für diese Themen: Daten- und Problemdarstellung, Operationalisierung, Wiederholbarkeit, Reproduzierbarkeit, Flexibilität, Erklärbarkeit und Fairness. Jedes Pattern enthält eine Beschreibung des Problems, eine Vielzahl möglicher Lösungen und Empfehlungen für die Auswahl der besten Technik für Ihre Situation. Biographical note: Valliappa Lakshmanan ist Global Head für Datenanalyse und KI-Lösungen bei Google Cloud. Sara Robinson ist Developer Advocate im Google-Cloud-Team, sie ist spezialisiert auf Machine Learning. Michael Munn ist ML Solutions Engineer bei Google. Er unterstützt Kunden bei der Entwicklung, Implementierung und Bereitstellung von Machine-Learning-Modellen.
Entwurfsmuster --- Python --- Künstliche Intelligenz --- Neuronale Netze --- KI --- Artificial Intelligence --- Deep Learning --- DevOps --- Maschinelles Lernen --- scikit-learn --- AI --- Statistische Datenanalyse --- TensorFlow --- PyTorch --- Machine Learning Operations
Choose an application
Long description: Biographical note:
Datenanalyse --- Big Data --- Datenverarbeitung --- Python --- Neuronale Netze --- Algorithmen --- buch --- Machine Learning --- clusteranalyse --- regressionsanalyse --- Deep Learning --- NumPy --- Predictive Analytics --- Data Science --- SciPy --- sentiment analyse --- TensorFlow --- Scikit Learn --- mitp
Choose an application
Through a series of recent breakthroughs, deep learning has boosted the entire field of machine learning. Now, even programmers who know close to nothing about this technology can use simple, efficient tools to implement programs capable of learning from data. This practical book shows you how.By using concrete examples, minimal theory, and two production-ready Python frameworks-Scikit-Learn and TensorFlow-author Aurélien Géron helps you gain an intuitive understanding of the concepts and tools for building intelligent systems. You'll learn a range of techniques, starting with simple linear regression and progressing to deep neural networks. With exercises in each chapter to help you apply what you've learned, all you need is programming experience to get started.
Machine Learning --- Artificial intelligence --- Machine learning. --- Apprentissage automatique --- Computer algorithms. --- Algorithmes --- Artificial intelligence. Robotics. Simulation. Graphics --- Artificial intelligence. --- Python (Computer program language) --- TensorFlow. --- Apprentissage automatique. --- Intelligence artificielle. --- Python (langage de programmation) --- Algorithmes. --- TensorFlow --- Scikit-Learn --- Python (Computer program language). --- machine learning --- kunstmatige intelligentie (artificiële intelligentie) --- Scikit-learn --- Keras --- deep learning
Choose an application
La 4e de couv. indique : "Le machine learning (ou apprentissage automatique) est désormais partie intégrante de nombreuses applications commerciales et projets de recherche. Mais ce domaine ne reste pas l'apanage des grandes entreprises dotées d'un département en recherche et développement. Si vous connaissez un minimum le langage de programmation Python, vous apprendrez grâce à ce livre à concevoir vos propres solutions de machine learning. Avec la masse de données qui circulent actuellement, la seule limite que peuvent connaître vos applications de machine learning, c'est votre imagination. Cet ouvrage énumère les étapes nécessaires à la création d'une application de machine learning réussie avec Python et la librairie scikit-learn. Ses auteurs se sont efforcés de ne pas trop insister sur les aspects mathématiques de l'apprentissage automatique, mais plutôt sur les utilisations pratiques de ces algorithmes. Si vous êtes déjà quelque peu familiarisé avec les librairies NumPy et matplotlib, vous n'en serez que plus à l'aise. Au programme de ce livre : concepts fondamentaux et applications de machine learning ; avantages et inconvénients d'utiliser les algorithmes de machine learning les plus courants ; comment représenter les données traitées par le machine learning, et sur lesquelles se concentrer ; méthodes avancées d'évaluation de modèle et ajustement des paramètres ; le concept de pipeline pour le chaînage des modèles et l'encapsulation du flux de travail ; techniques de traitement des données textuelles ; suggestions pour améliorer vos compétences en apprentissage automatique et en sciences des données."
Python (Computer program language) --- Data mining. --- Apprentissage automatique. --- Python (langage de programmation) --- Python (Langage de programmation) --- Exploration de données (Informatique) --- Scikit-Learn (logiciel) --- Exploration de données. --- Machine learning --- Apprentissage automatique
Choose an application
This book is about JIDOKA, a Japanese management technique coined by Toyota that consists of imbuing machines with human intelligence. The purpose of this compilation of research articles is to show industrial leaders innovative cases of digitization of value creation processes that have allowed them to improve their performance in a sustainable way. This book shows several applications of JIDOKA in the quest towards an integration of human and AI within Industry 4.0 Cyber Physical Manufacturing Systems. From the use of artificial intelligence to advanced mathematical models or quantum computing, all paths are valid to advance in the process of human–machine integration.
healthy operator 4.0 --- human–cyber–physical system --- industrial internet of things --- industry 4.0 --- smart workplaces --- EEG sensors --- manufacturing systems --- shopfloor management --- machine learning --- deep learning --- reference architecture model --- interoperability --- digital twin --- distributed ledger technology --- GDPR --- RAMI 4.0 --- LASFA --- quantum computing --- strategic organizational design --- Industry 4.0 --- complex networks --- cyber-physical systems --- lean management systems --- quantum strategic organizational design --- quantum circuits --- quantum simulation --- JIDOKA --- Operator 4.0 --- process variability --- integration explaining variability --- quantum approximate optimization algorithm --- value–stream networks --- optimization --- maintenance interval --- maintenance model --- semi-Markov process --- right-censored data --- finite horizon --- maintenance cost --- Cyber-Physical Systems --- Lean Manufacturing --- Directed Acyclic Graphs --- scikit-learn --- pipegraph --- machine learning models
Choose an application
This book is about JIDOKA, a Japanese management technique coined by Toyota that consists of imbuing machines with human intelligence. The purpose of this compilation of research articles is to show industrial leaders innovative cases of digitization of value creation processes that have allowed them to improve their performance in a sustainable way. This book shows several applications of JIDOKA in the quest towards an integration of human and AI within Industry 4.0 Cyber Physical Manufacturing Systems. From the use of artificial intelligence to advanced mathematical models or quantum computing, all paths are valid to advance in the process of human–machine integration.
Technology: general issues --- History of engineering & technology --- healthy operator 4.0 --- human–cyber–physical system --- industrial internet of things --- industry 4.0 --- smart workplaces --- EEG sensors --- manufacturing systems --- shopfloor management --- machine learning --- deep learning --- reference architecture model --- interoperability --- digital twin --- distributed ledger technology --- GDPR --- RAMI 4.0 --- LASFA --- quantum computing --- strategic organizational design --- Industry 4.0 --- complex networks --- cyber-physical systems --- lean management systems --- quantum strategic organizational design --- quantum circuits --- quantum simulation --- JIDOKA --- Operator 4.0 --- process variability --- integration explaining variability --- quantum approximate optimization algorithm --- value–stream networks --- optimization --- maintenance interval --- maintenance model --- semi-Markov process --- right-censored data --- finite horizon --- maintenance cost --- Cyber-Physical Systems --- Lean Manufacturing --- Directed Acyclic Graphs --- scikit-learn --- pipegraph --- machine learning models --- healthy operator 4.0 --- human–cyber–physical system --- industrial internet of things --- industry 4.0 --- smart workplaces --- EEG sensors --- manufacturing systems --- shopfloor management --- machine learning --- deep learning --- reference architecture model --- interoperability --- digital twin --- distributed ledger technology --- GDPR --- RAMI 4.0 --- LASFA --- quantum computing --- strategic organizational design --- Industry 4.0 --- complex networks --- cyber-physical systems --- lean management systems --- quantum strategic organizational design --- quantum circuits --- quantum simulation --- JIDOKA --- Operator 4.0 --- process variability --- integration explaining variability --- quantum approximate optimization algorithm --- value–stream networks --- optimization --- maintenance interval --- maintenance model --- semi-Markov process --- right-censored data --- finite horizon --- maintenance cost --- Cyber-Physical Systems --- Lean Manufacturing --- Directed Acyclic Graphs --- scikit-learn --- pipegraph --- machine learning models
Listing 1 - 10 of 11 | << page >> |
Sort by
|