Deep Learning and its Applications using Python

Deep Learning and its Applications using Python

by Niha Kamal Basha, Surbhi Bhatia Khan, Abhishek Kumar, Arwa Mashat
Released October 2023
Publisher(s): Wiley-Scrivener
ISBN: 9781394166466

Read it now on the O’Reilly learning platform with a 10-day free trial.

O’Reilly members get unlimited access to books, live events, courses curated by job role, and more from O’Reilly and nearly 200 top publishers.

Start your free trial

Book description

This book thoroughly explains deep learning models and how to use Python programming to implement them in applications such as NLP, face detection, face recognition, face analysis, and virtual assistance (chatbot, machine translation, etc.). It provides hands-on guidance in using Python for implementing deep learning application models. It also identifies future research directions for deep learning.

Table of contents

  1. Cover
  2. Table of Contents
  3. Series Page
  4. Title Page
  5. Copyright Page
  6. Preface
  7. 1 Introduction to Deep Learning
    1. 1.1 History of Deep Learning
    2. 1.2 A Probabilistic Theory of Deep Learning
    3. 1.3 Back Propagation and Regularization
    4. 1.4 Batch Normalization and VC Dimension
    5. 1.5 Neural Nets—Deep and Shallow Networks
    6. 1.6 Supervised and Semi-Supervised Learning
    7. 1.7 Deep Learning and Reinforcement Learning
    8. References
  8. 2 Basics of TensorFlow
    1. 2.1 Tensors
    2. 2.2 Computational Graph and Session
    3. 2.3 Constants, Placeholders, and Variables
    4. 2.4 Creating Tensor
    5. 2.5 Working on Matrices
    6. 2.6 Activation Functions
    7. 2.7 Loss Functions
    8. 2.8 Common Loss Function
    9. 2.9 Optimizers
    10. 2.10 Metrics
    11. References
  9. 3 Understanding and Working with Keras
    1. 3.1 Major Steps to Deep Learning Models
    2. 3.2 Load Data
    3. 3.3 Pre-Process Data
    4. 3.4 Define the Model
    5. 3.5 Compile the Model
    6. 3.6 Fit and Evaluate the Mode
    7. 3.7 Prediction
    8. 3.8 Save and Reload the Model
    9. 3.9 Additional Steps to Improve Keras Models
    10. 3.10 Keras with TensorFlow
    11. References
  10. 4 Multilayer Perceptron
    1. 4.1 Artificial Neural Network
    2. 4.2 Single-Layer Perceptron
    3. 4.3 Multilayer Perceptron
    4. 4.4 Logistic Regression Model
    5. 4.5 Regression to MLP in TensorFlow
    6. 4.6 TensorFlow Steps to Build Models
    7. 4.7 Linear Regression in TensorFlow
    8. 4.8 Logistic Regression Mode in TensorFlow
    9. 4.9 Multilayer Perceptron in TensorFlow
    10. 4.10 Regression to MLP in Keras
    11. 4.11 Log-Linear Model
    12. 4.12 Keras Neural Network for Linear Regression
    13. 4.13 Keras Neural Network for Logistic Regression
    14. 4.14 MLPs on the Iris Data
    15. 4.15 MLPs on MNIST Data (Digit Classification)
    16. 4.16 MLPs on Randomly Generated Data
    17. References
  11. 5 Convolutional Neural Networks in Tensorflow
    1. 5.1 CNN Architectures
    2. 5.2 Properties of CNN Representations
    3. 5.3 Convolution Layers, Pooling Layers – Strides - Padding and Fully Connected Layer
    4. 5.4 Why TensorFlow for CNN Models?
    5. 5.5 TensorFlow Code for Building an Image Classifier for MNIST Data
    6. 5.6 Using a High-Level API for Building CNN Models
    7. 5.7 CNN in Keras
    8. 5.8 Building an Image Classifier for MNIST Data in Keras
    9. 5.9 Building an Image Classifier with CIFAR-10 Data
    10. 5.10 Define the Model Architecture
    11. 5.11 Pre-Trained Models
    12. References
  12. 6 RNN and LSTM
    1. 6.1 Concept of RNN
    2. 6.2 Concept of LSTM
    3. 6.3 Modes of LSTM
    4. 6.4 Sequence Prediction
    5. 6.5 Time-Series Forecasting with the LSTM Model
    6. 6.6 Speech to Text
    7. 6.7 Examples Using Each API
    8. 6.8 Text-to-Speech Conversion
    9. 6.9 Cognitive Service Providers
    10. 6.10 The Future of Speech Analytics
    11. References
  13. 7 Developing Chatbot’s Face Detection and Recognition
    1. 7.1 Why Chatbots?
    2. 7.2 Designs and Functions of Chatbot’s
    3. 7.3 Steps for Building a Chatbot’s
    4. 7.4 Best Practices of Chatbot Development
    5. 7.5 Face Detection
    6. 7.6 Face Recognition
    7. 7.7 Face Analysis
    8. 7.8 OpenCV—Detecting a Face, Recognition and Face Analysis
    9. 7.9 Deep Learning–Based Face Recognition
    10. 7.10 Transfer Learning
    11. 7.11 API’s
    12. References
  14. 8 Advanced Deep Learning
    1. 8.1 Deep Convolutional Neural Networks (AlexNet)
    2. 8.2 Networks Using Blocks (VGG)
    3. 8.3 Network in Network (NiN)
    4. 8.4 Networks with Parallel Concatenations (GoogLeNet)
    5. 8.5 Residual Networks (ResNet)
    6. 8.6 Densely Connected Networks (DenseNet)
    7. 8.7 Gated Recurrent Units (GRU)
    8. 8.8 Long Short-Term Memory (LSTM)
    9. 8.9 Deep Recurrent Neural Networks (D-RNN)
    10. 8.10 Bidirectional Recurrent Neural Networks (Bi-RNN)
    11. 8.11 Machine Translation and the Dataset
    12. 8.12 Sequence to Sequence Learning
    13. References
  15. 9 Enhanced Convolutional Neural Network
    1. 9.1 Introduction
    2. 9.2 Deep Learning-Based Architecture for Absence Seizure Detection
    3. 9.3 EEG Signal Pre-Processing Strategy and Channel Selection
    4. 9.4 Input Formulation and Augmentation of EEG Signal for Deep Learning Model
    5. 9.5 Deep Learning Based Feature Extraction and Classification
    6. 9.6 Performance Analysis
    7. 9.7 Summary
    8. References
  16. 10 Conclusion
    1. 10.1 Introduction
    2. 10.2 Future Research Direction and Prospects
    3. 10.3 Research Challenges in Deep Learning
    4. 10.4 Practical Deep Learning Case Studies
    5. 10.5 Summary
    6. References
  17. Index
  18. End User License Agreement

Product information

  • Title: Deep Learning and its Applications using Python
  • Author(s): Niha Kamal Basha, Surbhi Bhatia Khan, Abhishek Kumar, Arwa Mashat
  • Release date: October 2023
  • Publisher(s): Wiley-Scrivener
  • ISBN: 9781394166466