Deep Learning with Real-World Projects

Deep Learning with Real-World Projects

by Geekshub Pvt. Ltd.
Released July 2019
Publisher(s): Packt Publishing
ISBN: 9781838985721

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

Video description

Want to become a good data scientist? Then this is the right course for you.

This course has been designed by IIT professionals who have mastered mathematics and data science. We will be covering complex theory, algorithms, and coding libraries in a very simple way that can be easily grasped by any beginner.

We will walk you step-by-step into the world of deep learning. Each video seeks to improve your understanding of the challenging field of Deep Learning from a beginner to an advanced level.

We will cover artificial neural networks, feedforward networks, backpropagation, regularization, convolution neural networks, practical on CNN, two real-world projects for CNN, transfer learning, recurrent neural networks, advanced RNN, a case study on NLP (Natural Language Processing), generate automatic programming code, and build a solid foundation for Python and machine learning.

We will be solving a few real-world projects during this course and their complete solutions are also provided so that students can easily implement what has been taught.

By the end of the course, you will be able to use Python’s deep learning algorithms in real life.

What You Will Learn

  • Learn to use Matplotlib for data visualization
  • Learn to use Seaborn for statistical plots
  • Learn to use NumPy and Pandas for data analysis
  • Learn all the mathematics required to understand deep learning algorithms
  • Learn all statistical principles and become a deep learning expert
  • Learn end to end data science solutions

Audience

A beginner in Python or any other object-oriented programming language should find this course helpful. Those who are already working on analytics and machine learning models and looking to leverage deep learning technologies to improve their problem-solving capacity should benefit from this course. Working professionals looking for a career transition to data science roles will be able to upskill.

About The Author

Geekshub Pvt. Ltd.: Geekshub is an online education company in the field of big data and analytics. Their aim as a team is to provide the best skill-set to their customers to make them job-ready and prepare them to crack any challenge. They have the best trainers for cutting-edge technologies such as machine learning, deep learning, Natural Language Processing (NLP), reinforcement learning, and data science. Their instructors are people who graduated from IIT, MIT and Standford. They are passionate about teaching the topics using curated real-world case studies that calibrate the learning experience of students.

Table of contents

  1. Chapter 1 : Course Introduction
    1. Introduction
    2. History of Deep Learning
    3. Perceptrons
    4. Multi-Level Perceptrons
    5. Neural Network Playground
    6. Representations
    7. Training Neural Network - Part 1
    8. Training Neural Network - Part 2
    9. Training Neural Network - Part 3
    10. Activation Functions
  2. Chapter 2 : Artificial Neural Networks-Introduction
    1. Introduction
    2. Deep Learning
    3. Understanding the Human Brain
    4. Perceptron
    5. Perceptron for Classifiers
    6. Perceptron in Depth
    7. Homogeneous Coordinate
    8. Example for Perceptron
    9. Multi-Classifier
    10. Neural Networks
    11. Input Layer
    12. Output Layer
    13. Sigmoid Function
    14. Understanding MNIST
    15. Assumptions in Neural Networks
    16. Training in Neural Networks
    17. Understanding Notations
    18. Activation Functions
  3. Chapter 3 : ANN - Feed Forward Network
    1. Introduction
    2. Online Offline Mode
    3. Bidirectional RNN
    4. Understanding Dimensions
    5. Pseudocode
    6. Pseudocode for Batch
    7. Vectorized Methods
  4. Chapter 4 : Backpropagation
    1. Introduction
    2. Introducing Loss Function
    3. Backpropagation Training - Part 1
    4. Backpropagation Training - Part 2
    5. Backpropagation Training - Part 3
    6. Backpropagation Training - Part 4
    7. Backpropagation Training - Part 5
    8. Sigmoid Function
    9. Backpropagation Training - Part 6
    10. Backpropagation Training - Part 7
    11. Backpropagation Training - Part 8
    12. Backpropagation Training - Part 9
    13. Backpropagation Training - Part 10
    14. Pseudocode
    15. SGD
    16. Finding Global Minima
    17. Training for Batches
  5. Chapter 5 : Regularization
    1. Introduction to Regularization
    2. Dropouts Part 1
    3. Dropouts Part 2
    4. Batch Normalization - Part 1
    5. Batch Normalization - Part 2
    6. Batch Normalization - Part 3
    7. Introducing TensorFlow
    8. Introducing Keras
  6. Chapter 6 : Convolution Neural Networks
    1. Introduction
    2. Applications for CNN
    3. Idea Behind CNN - Part 1
    4. Idea Behind CNN - Part 2
    5. Images
    6. Video
    7. Convolution - Part 1
    8. Convolution - Part 2
    9. Stride and Padding
    10. Padding
    11. Formulas
    12. Weight and Bias
    13. Feature Map
    14. Pooling
    15. Combining Network
  7. Chapter 7 : CNN-Keras
    1. Introduction
    2. VGG16 (Visual Geometry Group)
    3. Practical on CNN: Case Study – Part 1
    4. Practical on CNN: Case Study – Part 2
    5. Practical on CNN: Case Study – Part 3
    6. Practical on CNN: Case Study – Part 4
    7. Practical on CNN: Case Study – Part 5
  8. Chapter 8 : CNN-Transfer Learning
    1. Introduction
    2. AlexNet
    3. GoogleNet
    4. ResNet - Part 1
    5. ResNet - Part 2
    6. Transfer Learning - Part 1
    7. Transfer Learning - Part 2
    8. Transfer Learning - Part 3
    9. Transfer Learning - Part 4
    10. Transfer Learning - Part 5
    11. Transfer Learning - Part 6
    12. Case Study - Part 1
    13. Case Study - Part 2
    14. Case Study - Part 3
    15. Analysis - Part 1
    16. Analysis - Part 2
  9. Chapter 9 : CNN-Industry Live Project: Playing with Real-World Natural Images
    1. Introduction
    2. Working with Flower Images: Case Study - Part 1
    3. Working with Flower Images: Case Study - Part 2
    4. Working with Flower Images: Case Study - Part 3
    5. Working with Flower Images: Case Study - Part 4
    6. Working with Flower Images: Case Study - Part 5
    7. Working with Flower Images: Case Study - Part 6
    8. Working with Flower Images: Case Study - Part 7
    9. Working with Flower Images: Case Study - Part 8
    10. Working with Flower Images: Case Study - Part 9
    11. Working with Flower Images: Case Study - Part 10
    12. Working with Flower Images: Case Study - Part 11
    13. Working with Flower Images: Case Study - Part 12
    14. Working with Flower Images: Case Study - Part 13
    15. Working with Flower Images: Case Study - Part 14
  10. Chapter 10 : CNN-Industry Live Project: Find Medical Abnormalities and Save a Life
    1. Introduction
    2. Working with X-Ray images: Case Study - Part 1
    3. Working with X-Ray images: Case Study - Part 2
    4. Working with X-Ray images: Case Study - Part 3
    5. Working with X-Ray images: Case Study - Part 4
    6. Working with X-Ray images: Case Study - Part 5
    7. Working with X-Ray images: Case Study - Part 6
  11. Chapter 11 : Recurrent Neural Networks: Introduction
    1. Introduction to RNN
    2. RNN - Part 1
    3. RNN - Part 2
    4. RNN Formula
    5. Architecture
    6. Batch data
    7. Simplified Notations
    8. Types of RNN - Part 1
    9. Types of RNN - Part 2
    10. Training RNN
    11. One-to-Many
    12. Vanishing Gradient
  12. Chapter 12 : Recurrent Neural Networks: LSTM
    1. Introduction
    2. Online Offline Mode
    3. Bidirectional RNN
    4. LSTM - Part 1
    5. LSTM - Part 2
    6. LSTM - Part 3
    7. LSTM - Part 4
    8. LSTM - Part 5
    9. LSTM Equation
    10. Gated Recurrent Network (GRU)
  13. Chapter 13 : Recurrent Neutral Networks: Part-Of-Speech Tagger
    1. Part-Of-Speech Tagger Case-Study (Part-1)
    2. Part-Of-Speech Tagger Case- Study (Part-2)
    3. Part-Of-Speech Tagger Case- Study (Part-3)
    4. Part-Of-Speech Tagger Case- Study (Part-4)
    5. Part-Of-Speech Tagger Case- Study (Part-5)
    6. Part-Of-Speech Tagger Case- Study (Part-6)
    7. Part-Of-Speech Tagger Case- Study (Part-7)
    8. Part-Of-Speech Tagger Case- Study (Part-8)
    9. Part-Of-Speech Tagger Case- Study (Part-9)
  14. Chapter 14 : Text Generation Using RNN
    1. Text Generation: Code Generator Case- Study (Part-1)
    2. Text Generation: Code Generator Case- Study (Part-2)
    3. Text Generation: Code Generator Case- Study (Part-3)
    4. Text Generation: Code Generator Case- Study (Part-4)
  15. Chapter 15 : Prerequisite - Python Fundamentals
    1. Installation of Python and Anaconda
    2. Python Introduction
    3. Variables in Python
    4. Numeric Operations in Python
    5. Logical Operations
    6. If Else Loop
    7. For While Loop
    8. Functions
    9. Strings: Part 1
    10. Strings: Part 2
    11. List: Part 1
    12. List: Part 2
    13. List: Part 3
    14. List: Part 4
    15. Tuples
    16. Sets
    17. Dictionaries
    18. Comprehension
  16. Chapter 16 : Prerequisite - NumPy
    1. Introduction
    2. NumPy Operations: Part 1
    3. NumPy Operations: Part 2
  17. Chapter 17 : Prerequisite - Pandas
    1. Introduction
    2. Series
    3. DataFrame
    4. Operations: Part 1
    5. Operations: Part 2
    6. Indexes
    7. loc and iloc
    8. Reading CSV
    9. Merging: Part 1
    10. groupby
    11. Merging: Part 2
    12. Pivot Tables
  18. Chapter 18 : Prerequisite - Some Fun with Math
    1. Linear Algebra: Vectors
    2. Linear Algebra: Matrix: Part 1
    3. Linear Algebra: Matrix: Part 2
    4. Linear Algebra: Going from 2D to nD: Part 1
    5. Linear Algebra: Going from 2D to nD: Part 2
  19. Chapter 19 : Prerequisite - Data Visualization
    1. Matplotlib
    2. Seaborn
    3. Case Study
    4. Seaborn on Time Series Data
  20. Chapter 20 : Prerequisite - Simple Linear Regression
    1. Introduction to Machine Learning
    2. Types of Machine Learning
    3. Introduction to Linear Regression (LR)
    4. How LR Works?
    5. Some Fun with Math Behind LR
    6. R Square
    7. LR Case Study: Part 1
    8. LR Case Study: Part 2
    9. LR Case Study: Part 3
    10. Residual Square Error (RSE)
  21. Chapter 21 : Prerequisite - Gradient Descent
    1. Prerequisite for Gradient Descent: Part 1
    2. Prerequisite for Gradient Descent: Part 2
    3. Cost Functions
    4. Defining Cost Functions More Formally
    5. Gradient Descent
    6. Optimization
    7. Closed Form Versus Gradient Descent
    8. Gradient Descent Case Study
  22. Chapter 22 : Prerequisite - Classification: KNN
    1. Introduction to Classification
    2. Defining Classification Mathematically
    3. Introduction to KNN
    4. Accuracy of KNN
    5. Effectiveness of KNN
    6. Distance Metrics
    7. Distance Metrics: Part 2
    8. Finding k
    9. KNN on Regression
    10. Case Study
    11. Classification Case 1
    12. Classification Case 2
    13. Classification Case 3
    14. Classification Case 4
  23. Chapter 23 : Prerequisite - Logistic Regression
    1. Introduction
    2. Sigmoid Function
    3. Log Odds
    4. Case Study
  24. Chapter 24 : Prerequisite - Advanced Machine Learning Algorithms
    1. Introduction
    2. Example: Part 1
    3. Example: Part 2
    4. Optimal Solution
    5. Case Study
    6. Regularization
    7. Ridge and Lasso
    8. Case Study
    9. Model Selection
    10. Adjusted R Square

Product information

  • Title: Deep Learning with Real-World Projects
  • Author(s): Geekshub Pvt. Ltd.
  • Release date: July 2019
  • Publisher(s): Packt Publishing
  • ISBN: 9781838985721