| Autore |
Ketkar Nikhil
|
| Edizione | [1st ed. 2017.] |
| Pubbl/distr/stampa |
[Place of publication not identified] : , : Apress, , [2017]
|
| Descrizione fisica |
1 online resource (XV, 160 p. 93 illus., 65 illus. in color.)
|
| Disciplina |
006.31
|
| Soggetto topico |
Machine learning
|
| ISBN |
1-4842-2766-2
|
| Formato |
Materiale a stampa  |
| Livello bibliografico |
Monografia |
| Lingua di pubblicazione |
eng
|
| Nota di contenuto |
Chapter 1: An intuitive look at the fundamentals of deep learning based on practical applications -- Chapter 2: A survey of the current state-of-the-art implementations of libraries, tools and packages for deep learning and the case for the Python ecosystem -- Chapter 3: A detailed look at Keras [1], which is a high level framework for deep learning suitable for beginners to understand and experiment with deep learning -- Chapter 4: A detailed look at Theano [2], which is a low level framework for implementing architectures and algorithms in deep learning from scratch -- Chapter 5: A detailed look at Caffe [3], which is highly optimized framework for implementing some of the most popular deep learning architectures (mainly computer vision) -- Chapter 6: A brief introduction to GPUs and why they are a game changer for Deep Learning -- Chapter 7: A brief introduction to Automatic Differentiation -- Chapter 8: A brief introduction to Backpropagation and Stochastic Gradient Descent -- Chapter 9: A survey of Deep Learning Architectures -- Chapter 10: Advice on running large scale experiments in deep learning and taking models to production. - Chapter 11: Introduction to Tensorflow. - Chapter 12: Introduction to PyTorch. -Chapter 13: Regularization Techniques. - Chapter 14: Training Deep Leaning Models.
|
| Record Nr. | UNINA-9910254855303321 |
Info
Deep learning with Python : learn best practices of deep learning models with PyTorch / / Nikhil Ketkar, Jojo Moolayil
