Lavoisier S.A.S.
14 rue de Provigny
94236 Cachan cedex
FRANCE

Heures d'ouverture 08h30-12h30/13h30-17h30
Tél.: +33 (0)1 47 40 67 00
Fax: +33 (0)1 47 40 67 02


Url canonique : www.lavoisier.fr/livre/notice.asp?ouvrage=4773904
Url courte ou permalien : www.lavoisier.fr/livre/notice.asp?ouvrage=4773904

0 article 

 Frais de port 0,01€*

Exclusivité web : à partir de 35 euros d’achat, frais de port à 1 centime pour les expéditions vers la France métropolitaine, la Suisse et l’UE avec Colissimo ou GLS

Pro Deep Learning with TensorFlow 2.0 (2nd Ed., 2nd ed.) A Mathematical Approach to Advanced Artificial Intelligence in Python

Langue : Anglais

Auteur :

Couverture de l’ouvrage Pro Deep Learning with TensorFlow 2.0

This book builds upon the foundations established in its first edition, with updated chapters and the latest code implementations to bring it up to date with Tensorflow 2.0.

Pro Deep Learning with TensorFlow 2.0 begins with the mathematical and core technical foundations of deep learning. Next, you will learn about convolutional neural networks, including new convolutional methods such as dilated convolution, depth-wise separable convolution, and their implementation. You?ll then gain an understanding of natural language processing in advanced network architectures such as transformers and various attention mechanisms relevant to natural language processing and neural networks in general. As you progress through the book, you?ll explore unsupervised learning frameworks that reflect the current state of deep learning methods, such as autoencoders and variational autoencoders. The final chapter covers the advanced topic of generative adversarial networks and their variants, such as cycle consistency GANs and graph neural network techniques such as graph attention networks and GraphSAGE.

Upon completing this book, you will understand the mathematical foundations and concepts of deep learning, and be able to use the prototypes demonstrated to build new deep learning applications.

What You Will Learn

  • Understand full-stack deep learning using TensorFlow 2.0
  • Gain an understanding of the mathematical foundations of deep learning
  • Deploy complex deep learning solutions in production using TensorFlow 2.0
  • Understand generative adversarial networks, graph attention networks, and GraphSAGE

Who This Book Is For:

Data scientists and machine learning professionals, software developers, graduate students, and open source enthusiasts.
Chapter 1:  Mathematical Foundations
Chapter Goal: Setting the mathematical base for machine learning and deep learning .
No of pages 100
Sub -Topics
1. Linear algebra 
2. Calculus
3. Probability
4. Formulation of machine learning algorithms and optimization techniques.

Chapter 2:  Introduction to Deep learning Concepts and Tensorflow 2.0 
Chapter Goal: Setting the foundational base for deep learning and introduction to Tensorflow 2.0 programming paradigm. 
No of pages: 75
Sub - Topics:  
5. Deep learning and its evolution.
6. Evolution of the learning techniques: from perceptron based learning to back-propagation
7. Different deep learning objectives functions for supervised and unsupervised learning.
8. Tensorflow 2.0
9. GPU

Chapter 3: Convolutional Neural networks
Chapter Goal: The mathematical and technical aspects of convolutional neural network
No of pages: 80
1. Convolution operation
2. Analog and digital signal
3. 2D and 3D convolution, dilation  and depth-wise separable convolution 
4. Common image processing filter 
5. Convolutional neural network and components
6. Backpropagation through convolution and pooling layers
7. Translational invariance and equivariance 
8. Batch normalization
9. Image segmentation and localization methods (Moved from advanced Neural Network to here, to make room for Graph Neural Networks )

Chapter 4: Deep learning for Natural Language Processing 
Chapter Goal: Deep learning methods and natural language processing  
No of pages:
Sub - Topics: 
1.  Vector space model
2. Word2Vec 
3. Introduction to recurrent neural network and LSTM
4. Attention 
5. Transformer network architectures

Chapter 5: Unsupervised Deep Learning Methods
Chapter Goal: Foundations for different unsupervised deep learning techniques 
No of pages: 60
Sub - Topics: 
1. Boltzmann distribution
2. Bayesian inference
3. Restricted Boltzmann machines 
4. Auto Encoders and variation methods 

Chapter 6: Advanced Neural Networks 
Chapter Goal: Generative adversarial networks and graph neural networks 
No of pages: 70
Sub - Topics: 
1. Introduction to generative adversarial networks  
2. CycleGAN, LSGAN Wasserstein GAN
3. Introduction to graph neural network
4. Graph attention network and graph SAGE

Chapter 7: Reinforcement Learning 
Chapter Goal: Reinforcement Learning using Deep Learning 
No of pages: 50
Sub - Topics: 
1. Introduction to reinforcement learning and MDP formulation
2. Value based methods
3. DQN
4. Policy based methods
5. Reinforce and actor critic network in policy based formulations
6. Transition-less reinforcement learning and bandit methods



Santanu Pattanayak works as a Senior Staff Machine Learning Specialist at Qualcomm Corp R&D and is the author of Quantum Machine Learning with Python, published by Apress. He has more than 16 years of experience, having worked at GE, Capgemini, and IBM before joining Qualcomm. He graduated with a degree in electrical engineering from Jadavpur University, Kolkata and is an avid math enthusiast. Santanu has a master’s degree in data science from the Indian Institute of Technology (IIT), Hyderabad. He also participates in Kaggle competitions in his spare time, where he ranks in the top 500. Currently, he resides in Bangalore with his wife.

Teaches how to deploy deep learning applications using TensorFlow 2.0 in a relatively short period of time

Explains different deep learning methods for supervised and unsupervised machine learning

Covers advanced deep learning techniques such as Generative Adversarial Networks and Graph neural Networks

Date de parution :

Ouvrage de 652 p.

17.8x25.4 cm

Disponible chez l'éditeur (délai d'approvisionnement : 15 jours).

58,01 €

Ajouter au panier