Merkzettel Warenkorb
Produktbild: Learn Keras for Deep Neural Networks
- 12%

Learn Keras for Deep Neural Networks A Fast-Track Approach to Modern Deep Learning with Python

12% sparen

41,99 € UVP 48,14 €

inkl. gesetzl. MwSt., Versandkostenfrei

Lieferung nach Hause

Beschreibung

Produktdetails

Einband

Taschenbuch

Erscheinungsdatum

07.12.2018

Verlag

Apress

Seitenzahl

182

Maße (L/B/H)

23,5/15,5/1,2 cm

Gewicht

312 g

Auflage

1st ed.

Sprache

Englisch

ISBN

978-1-4842-4239-1

Beschreibung

Produktdetails

Einband

Taschenbuch

Erscheinungsdatum

07.12.2018

Verlag

Apress

Seitenzahl

182

Maße (L/B/H)

23,5/15,5/1,2 cm

Gewicht

312 g

Auflage

1st ed.

Sprache

Englisch

ISBN

978-1-4842-4239-1

Herstelleradresse

Springer-Verlag GmbH
Tiergartenstr. 17
69121 Heidelberg
DE

Email: GPSR Kontakt

Noch keine Bewertungen vorhanden

Verfassen Sie die erste Bewertung zu diesem Artikel

Helfen Sie anderen Kundinnen und Kunden durch Ihre Meinung.

Kundinnen und Kunden meinen

Bewertungen (0)
  • Produktbild: Learn Keras for Deep Neural Networks
  • SECTION 1: Prepares the reader with all the necessary gears to get started on the fast track ride in deep learning. Chapter 1: Deep Learning & Keras

    Chapter Goal: Introduce the reader to the deep learning and keras framework

    Sub -Topics

    1.    Exploring the popular Deep Learning frameworks

    2.     Overview of Keras, Pytorch, mxnet, Tensorflow, 

    3.      A closer look at Keras: What’s special about Keras?

     

    Chapter 2:  Keras in Action

    Chapter Goal: Help the reader to engage with hands-on exercises with Keras and implement the first basic deep neural network

    Sub - Topics       

    1.       A closer look at the deep learning building blocks

    2.       Exploring the keras building blocks for deep learning

    3.       Implementing a basic deep neural network with dummy data

    SECTION 2 – Help the reader embrace the core fundamentals in simple lucid language while abstracting the math and the complexities of model training and validation with the least amount of code without compromising on flexibility, scale and the required sophistication 

    Chapter 3: Deep Neural networks for Supervised Learning

    Chapter Goal: Embrace the core fundamentals of deep learning and its development

    Sub - Topics:     

    1.       Introduction to supervised learning

    2.       Classification use-case – implementing DNN

    3.       Regression use-case – implementing DNN

     

    Chapter 4: Measuring Performance for DNN

    Chapter Goal: Aid the reader in understanding the craft of validating deep neural networks

    Sub - Topics:

    1. Metrics for success – regression

    2. Analyzing the regression neural network performance

    3. Metrics for success – classification

    4. Analyzing the regression neural network performance

     

    SECTION 3 – Tuning and deploying robust DL models

    Chapter 5: Hyperparameter Tuning & Model Deployment

    Chapter Goal: Understand how to tune the model hyperparameters to achieve improved performance

    Sub - Topics:

    1.       Hyperparameter tuning for deep learning models

    2.       Model deployment and transfer learning

     

    Chapter 6: The Path Forward

    Chapter goal – Educate the reader about additional reading for advanced topics within deep learning.

    Sub - Topics:

    1.       What’s next for deep learning expertise?

    2.       Further reading

    3.       GPU for deep learning

    4.       Active research areas and breakthroughs in deep learning

    5.    Conclusion