{"product_id":"probabilistic-deep-learning-with-python-keras-and-tensorflow-probability","title":"Probabilistic Deep Learning: With Python, Keras and TensorFlow Probability","description":"Probabilistic Deep Learning is a hands-on guide to the principles that support neural networks. Learn to improve network performance with the right distribution for different data types, and discover Bayesian variants that can state their own uncertainty to increase accuracy. This book provides easy-to-apply code and uses popular frameworks to keep you focused on practical applications.\n\nSummary\nProbabilistic Deep Learning: With Python, Keras and TensorFlow Probability teaches the increasingly popular probabilistic approach to deep learning that allows you to refine your results more quickly and accurately without much trial-and-error testing. Emphasizing practical techniques that use the Python-based Tensorflow Probability Framework, you’ll learn to build highly-performant deep learning applications that can reliably handle the noise and uncertainty of real-world data.\n\nPurchase of the print book includes a free eBook in PDF, Kindle, and ePub formats from Manning Publications.\n\nAbout the technology\nThe world is a noisy and uncertain place. Probabilistic deep learning models capture that noise and uncertainty, pulling it into real-world scenarios. Crucial for self-driving cars and scientific testing, these techniques help deep learning engineers assess the accuracy of their results, spot errors, and improve their understanding of how algorithms work.\n\nAbout the book\nProbabilistic Deep Learning is a hands-on guide to the principles that support neural networks. Learn to improve network performance with the right distribution for different data types, and discover Bayesian variants that can state their own uncertainty to increase accuracy. This book provides easy-to-apply code and uses popular frameworks to keep you focused on practical applications.\n\nWhat's inside\n\nExplore maximum likelihood and the statistical basis of deep learning\nDiscover probabilistic models that can indicate possible outcomes\nLearn to use normalizing flows for modeling and generating complex distributions\nUse Bayesian neural networks to access the uncertainty in the model\n\nAbout the reader\nFor experienced machine learning developers.\n\nAbout the author\nOliver Dürr is a professor at the University of Applied Sciences in Konstanz, Germany. Beate Sick holds a chair for applied statistics at ZHAW and works as a researcher and lecturer at the University of Zurich. Elvis Murina is a data scientist.\n\nTable of Contents\n\nPART 1 - BASICS OF DEEP LEARNING\n\n1 Introduction to probabilistic deep learning\n\n2 Neural network architectures\n\n3 Principles of curve fitting\n\nPART 2 - MAXIMUM LIKELIHOOD APPROACHES FOR PROBABILISTIC DL MODELS\n\n4 Building loss functions with the likelihood approach\n\n5 Probabilistic deep learning models with TensorFlow Probability\n\n6 Probabilistic deep learning models in the wild\n\nPART 3 - BAYESIAN APPROACHES FOR PROBABILISTIC DL MODELS\n\n7 Bayesian learning\n\n8 Bayesian neural networks\u003cbr\u003eASIN: 1617296074\u003cbr\u003eVSKU: GBV.1617296074.G\u003cbr\u003eCondition: Good\u003cbr\u003eAuthor\/Artist:Duerr, Oliver|Sick, Beate|Murina, Elvis\u003cbr\u003eBinding: Paperback\u003cbr\u003e\u003cb\u003eNote:\u003c\/b\u003e Any images shown are stock photographs and product may differ from what is shown.  \u003cbr\u003e\u003cb\u003eCondition Notes\u003c\/b\u003e: Has a sturdy binding with some shelf wear. May have some markings or highlighting. Used copies may not include access codes or Cd's. Slight bending may be present.  \u003cbr\u003e","brand":"Good Books Company","offers":[{"title":"Default Title","offer_id":52810961289521,"sku":"GBV.1617296074.G","price":15.02,"currency_code":"USD","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0914\/3730\/2065\/files\/1617296074-0.jpg?v=1770936820","url":"https:\/\/goodbookscompany.org\/products\/probabilistic-deep-learning-with-python-keras-and-tensorflow-probability","provider":"Good Books Company","version":"1.0","type":"link"}