Deep Learning Cookbook (eBook)

Practical Recipes to Get Started Quickly

Douwe Osinga (Autor)

eBook Download: PDF

2018
252 Seiten
O'Reilly (Verlag)
978-1-4919-9581-5 (ISBN)

Infos

Deep learning doesnt have to be intimidating. Until recently, this machine-learning method required years of study, but with frameworks such as Keras and Tensorflow, software engineers without a background in machine learning can quickly enter the field. With the recipes in this cookbook, youll learn how to solve deep-learning problems for classifying and generating text, images, and music.Each chapter consists of several recipes needed to complete a single project, such as training a music recommending system. Author Douwe Osinga also provides a chapter with half a dozen techniques to help you if youre stuck. Examples are written in Python with code available on GitHub as a set of Python notebooks.Youll learn how to:Create applications that will serve real usersUse word embeddings to calculate text similarityBuild a movie recommender system based on Wikipedia linksLearn how AIs see the world by visualizing their internal stateBuild a model to suggest emojis for pieces of textReuse pretrained networks to build an inverse image search serviceCompare how GANs, autoencoders and LSTMs generate iconsDetect music styles and index song collections

Produkt-Details

• Erscheint lt. Verlag: 5.6.2018
• Sprache: englisch
• Themenwelt: Mathematik / Informatik ► Informatik ► Software Entwicklung
• Themenwelt: Mathematik / Informatik ► Informatik ► Theorie / Studium
• ISBN-10: 1-4919-9581-5 / 1491995815
• ISBN-13: 978-1-4919-9581-5 / 9781491995815