000			01824nam a2200205 4500
001			u3667
003			SIRSI
005			20250825174928.0
008			220928n2021 000 0 eng u
020			_a9781617298264
082			_a006.31 _bF357d 2021
100	1		_aFerlitsch, Andrew
245			_aDeep Learning Patterns and Practices
260			_aShelter Island: _bManning Publications, _c2021
300			_axxii, 447 páginas
505			_aPart 1. Deep learning fundamentals. Designing modern machine learning -- Deep neural networks -- Convolutional and residual neural networks -- Training fundamentals -- Part 2. Basic design pattern. Procedural design pattern -- Wide convolutional neural networks -- Alternative connectivity patterns -- Mobile convolutional neural networks -- Autoencoders -- Part 3. Working with pipelines. Hyperparameter tuning -- Transfer learning -- Data distributions -- Data pipeline -- Training and deployment pipeline.
520			_aDiscover best practices, design patterns, and reproducible architectures that will guide your deep learning projects from the lab into production. This awesome book collects and illuminates the most relevant insights from a decade of real-world deep learning experience. You'll build your skills and confidence with each interesting example. Deep learning patterns and practices is a deep dive into building successful deep learning applications. You'll save hours of trial-and-error by applying proven patterns and practices to your own projects. Tested code samples, real-world examples, and a brilliant narrative style make even complex concepts simple and engaging. Along the way, you'll get tips for deploying, testing, and maintaining your projects. _cSource other than the Library of Congress.
650			_aMachine learning
650			_aREDES NEURALES
999			_c2250 _d2250