Deep learning : a practitioner's approach / Josh Patterson and Adam Gibson.
By: Patterson, Josh (Consultant) [author.].
Contributor(s): Gibson, Adam [author.].
Publisher: Sebastopol, CA : O'Reilly, ©2017Edition: First edition.Description: 507 pages ; illustrations ; 24 cm.Content type: text Media type: unmediated Carrier type: volumeISBN: 9781491914250.Subject(s): Machine learning | Neural networks (Computer science) | Open source software | Machine learning | Neural networks (Computer science) | Open source softwareGenre/Form: Print books.| Current location | Call number | Status | Date due | Barcode | Item holds |
|---|---|---|---|---|---|
| On Shelf | QA325.5 .P38 2017 (Browse shelf) | Available | AU00000000014462 |
Browsing Alfaisal University Shelves , Shelving location: On Shelf Close shelf browser
|
|
|
|
|
|
|
||
| QA320 .J638 2017 Non-commutative analysis / | QA320 .K57 2017 Introduction to functional data analysis / | QA320 .S235 2017 A friendly approach to functional analysis / | QA325.5 .P38 2017 Deep learning : a practitioner's approach / | QA331.7 .A25 2003 Complex variables introduction and applications / | QA331.7 .B73 2011 Complex analysis with applications to flows and fields / | QA331.7 .K95 2016 Complex analysis : conformal inequalities and the Bieberbach conjecture / |
Includes bibliographical references and index.
A review of machine learning -- Foundations of neural networks and deep learning -- Fundamentals of deep networks -- Major architecture of deep networks -- Building deep networks -- Tuning deep networks -- Tuning specific deep network architectures -- Vectorization -- Using deep learning and DL4J on Spark -- What is artificial intelligence? -- RL4J and reinforcement learning -- Numbers everyone should know -- Neural networks and backpropagation: a mathematical approach -- Using the ND4J API -- Using DataVec -- Working with DL4J from source -- Setting up DL4J projects -- Setting up GPUs for DL4J projects -- Troubleshooting DL4J installations.
How can machine learning--especially deep neural networks--make a real difference in your organization? This hands-on guide not only provides practical information, but helps you get started building efficient deep learning networks. The authors provide the fundamentals of deep learning--tuning, parallelization, vectorization, and building pipelines--that are valid for any library before introducing the open source Deeplearning4j (DL4J) library for developing production-class workflows. Through real-world examples, you'll learn methods and strategies for training deep network architectures and running deep learning workflows on Spark and Hadoop with DL4J.--