New

Deep Learning Using Python

₹395.00

Availability: In Stock

Author(s): C Muthu, M C Prakash

Product Code: vn1000

This book Deep Learning Using Python has been designed for undergraduate and postgraduate students of Data Science, Artificial Intelligence, Computer Science, and related disciplines. It presents the fundamentals and advanced concepts of Deep Learning using Python through practical examples and hands-on exercises.

CONTENTS
Preface
Chapter: Introduction to Deep Learning
Introduction
Developing a Simple Deep Learning Program
Summary
Exercises
Chapter: Artificial Neural Networks
Introduction
Biological Neural Network
Artificial Neurons vs. Biological Neurons
Evolution of Artificial Neural Network
Basic Models of ANN
Applications for Artificial Neural Networks
Scope of Artificial Neural Networks
Architecture of an ANN
Layers and Neurons
Feed Forward Network
Weights, Biases and Parameters
Important Terminologies of ANN
Activation Functions (ReLU, ELU and SELU)
Learning Methods
Summary
Exercises
Chapter: Supervised Learning Networks
Introduction
Shallow Neural Networks
McCulloch-Pitts Network (MP Network)
Perceptron Network Model
Architecture and Learning Rule of Perceptron
Training Process, Algorithm and Flowchart for Perceptron
Perceptron for Multiple Output Classes
Linearly Separable Data
Multilayer Perceptron (MLP) / Back-Propagation Network
Architecture of Back-Propagation Network
Training Process and Algorithm for Back-Propagation Network
Optimization Techniques
Gradient Descent (GD) Method
Stochastic Gradient Descent (SGD)
Mini-Batch Gradient Descent (BGD)
Learning Factors for Back Propagation Network
Radial Basis Function Network (RBFN)
Architecture of RBFN
Algorithm for Training the RBFN
Summary
Exercises
Chapter: Image Classification using ANN
Introduction
Splitting the Dataset into Training and Test Sets
Designing the Artificial Neural Network
Specifying the Artificial Neural Network
Compiling the ANN
Fitting the ANN Model
Exploring the ANN’s Output
Complete Program
Training the ANN for Longer Duration
Summary
Exercises
Chapter: Convolutional Neural Networks
Introduction
Fashion MNIST Dataset
Splitting the Dataset into Training and Test Sets
Pre-processing the Data
Designing the Artificial Neural Network
Specifying the Artificial Neural Network
Compiling and Fitting the Neural Network
Complete Program
Importance of Convolutional Neural Network
Components of CNN Architecture
Convolutions
Pooling
Implementing the CNN
ReLU, ELU and SELU Activation Functions
Pooling Layers
Exploring the CNN
Unique Properties of CNN
Architectures of CNN
Applications of CNN
Summary
Exercises
Chapter: Building a CNN to Classify Multi-colour Images
Introduction
The Dogs-vs-Cats Dataset
Building the Convolutional Neural Network
Doing Prediction for the Test Data
Image Augmentation
Transfer Learning
Building a Multiclass Classifier
Data Set
Developing a CNN Model
Dropout Regularization
Summary
Exercises
Chapter: Disease Detection using CNN
Introduction
Leaf Disease Prediction
Data Preparation
Model Development
Accuracy Curve for the CNN Model
Prediction
Paddy Disease Detection
Dataset Overview
Model Development
Loss and Accuracy Curves for the CNN Model
Kidney Tumour Detection
Dataset Overview
Model Development
Accuracy and Loss Curves for the CNN
Prediction
Chapter: Recurrent Neural Networks
Introduction
Architecture of Recurrent Neural Network
LSTM and Bidirectional LSTM
Echo-State Network (ESN)
Challenges in Training RNN
Applications of Recurrent Neural Networks
Summary
Exercises
Chapter: Time Series Analysis using DL Models
Introduction
Common Attributes of Time Series
Trend
Seasonality
Random Component
Autocorrelation and Stationarity
Autocorrelation
Stationarity
Statistical Prediction of Temperature Time Series Values
Building an ANN for Temperature Time Series Prediction
Preparing a Windowed Dataset
Defining an ANN for Time Series Data
Creating a CNN for Time Series Data
Preparing Data
Defining a CNN Model for Temperature Prediction
Creating an RNN for Time Series Prediction
Summary
Exercises
Chapter: Sentiment Analysis using ANN
Introduction
Python Packages for NLP
Text Preprocessing
Tokenization
Stop Words Removal
Stemming
Lemmatization
PoS Tagging
Named Entity Recognition
Use of spaCy Package
Establishing Meaning for Words using Embeddings
Establishing Relative Meanings for Words
Using Vectors to Establish Meanings for Words
Using TensorFlow to Determine Embeddings of Words
Stock Market News Dataset
Building an ANN Model for News Sentiment Analysis
Reducing Overfitting in our Model
Adjusting the Learning Rate
Exploring Vocabulary Size
Exploring Embedding Dimensions
Exploring the Architecture of ANN Model
Using a Dropout Layer
Using Regularization Technique
Doing Prediction
Summary
Exercises
Chapter: RNN-based Sentiment Analyzer
Introduction
Creating an RNN Model
Stacking LSTMs
Optimizing Stacked LSTMs
Using Dropout Layer
Using Pretrained Embeddings with RNNs
Summary
Exercises
Chapter: Autoencoders
Introduction
Features and Types of Autoencoders
An ANN Autoencoder
Training the ANN Autoencoder
Convolutional Autoencoder
Variational Autoencoder
Architecture of VAE
Denoising the Data
Summary
Exercises
Chapter: Restricted Boltzmann Machines
Introduction
Types of Restricted Boltzmann Machine
Architecture of RBM
Training an RBM
Steps Involved in Implementation of RBM
Program for Developing a RBM Model
Deep Belief Network (DBN)
Training a DBN
Implementation of a DBN
Program for Developing a DBN Model
Summary
Exercises
Chapter: Transformers and GPT
Introduction
Word Embedding
Attention Mechanism
Transformers
Skip Connections
Norm-Add
Positional Embedding
Assembling a Transformer
Transformers in Action
BERT (Bidirectional Encoder Representations from Transformers)
BERT in Action
GPT-2 (Generative Pre-Training Model-2)
GPT-3
Summary
Exercises
Chapter: Generative Adversarial Networks
Introduction
Generator and Discriminator Networks
Learning from Experience
Training the Generator and Discriminator
Example for GAN
Deep Convolutional Generative Adversarial Network (DCGAN)
Summary
Exercises
Chapter: Text Generation
Introduction
Summary Generation
Installing Required Libraries
Importing the Pipeline
Defining a Function to Summarize Input Text
Creating and Launching Gradio Interface
Code Generation
Installing Required Libraries
Specifying the Processor Type
Loading the Model
Defining a Function to Generate Code
Creating and Launching Gradio Interface
A Basic Chatbot
Installing Required Libraries
Specifying the Processor Type
Loading the Model
Defining a Function to Refine the Response
Defining a Function that Takes in a Query and Provide the Response
Creating and Launching Gradio Interface
Chatbot for Querying a PDF Document
Importing Required Libraries
Specifying the Processor Type
Loading the Model Querying a PDF Document
Defining a Function to Extract Text from a PDF Document
Defining a Function that Takes in a Query and Provides the Response
Creating and Launching Gradio Interface
Chatbot using ChatInterface
Specifying OpenAI Key, Model, and System Message
Specifying the Processor Type
Defining the chat() function
Launching the Chat Interface
AI Sales Assistant for a Clothes Store
Importing the Required Libraries
Specifying OpenAI key, Model, and System Message
Specifying the Processor Type
Specifying the System Message
Defining the chat() function
Launching the Chat Interface
Improved Version of AI Sales Assistant
Importing the Required Libraries
Specifying OpenAI key, Model, and System Message
Specifying the Processor Type
Specifying the System Message
Defining the chat() function
Launching the Chat Interface
Webpage Summarizer
Specifying the OpenAI Key
Defining a Class
Specifying the System Prompt
Defining the stream_gpt() function
Defining the stream_brochure() function
Creating and Launching Gradio Interface
Company Brochure Generation
Importing Libraries and Specifying the OpenAI Key
Defining a Class
Specifying the System Prompt Regarding Links
Defining a Function to Form User Prompt Regarding Links
Defining a Function to Get Relevant Links
Defining a Function to Assemble All Details into Another Prompt
Defining the System Prompt
Defining a Function to Form User Prompt
Defining a Function to Create the Company Brochure
Exercises
Chapter: Image Generation
Introduction
Evolution of Diffusion Models
UNET Model
Stable Diffusion Model
Text-to-Image Generation
Model Description
Installing Required Libraries
Importing Libraries and Initializing API
Defining a Function to Generate Image
Creating and Launching Gradio Interface
Complete Program
Face Mask Detection
Data Preprocessing
Loading the Model
The classify_image() function
Model Deployment using Gradio
Complete Program
Object Detection
Importing the Libraries
Loading the Model
Define a Function to Perform Object Detection
Model Deployment using Gradio
Complete Program
Image Captioning Application
Installing Required Libraries
Loading the Image Captioning Model
Setting up Prerequisites for the Image Captioning Application
Converting an Image to a Base64 String
Defining the Captioner Function
Closing Any Existing Gradio Interfaces
Creating and Launching the Gradio Web Application
Complete Program
Exercises
Chapter: Audio Generation
Introduction
Speech-to-Text Conversion
Text-to-Speech Conversion
AudioLM, MusicLM, AudioGen, MusicGen
Audio Diffusion and Riffusion
Dance Diffusion
A Multimodal AI Assistant
Importing Required Libraries
Specifying the Processor Type
Defining a Function to Generate an Image of a Tourist Spot
Generating an Image of a Tourist Spot
Defining a Function to Get Ticket Price
Defining a Function to Orally Tell the Ticket Price
Defining a Function to Generate Output
Creating and Launching the Gradio Interface
Exercises