Python for Deep Learning — Build Neural Networks in Python

Video description

Python is famed as one of the best programming languages for its flexibility. It works in almost all fields, from web development to developing financial applications. However, it's no secret that Python’s best application is in deep learning and artificial intelligence tasks.

We will start with an introduction to deep learning where we will focus on the fundamentals of the deep learning theory and learn how to use deep learning in Python. Followed by this we will move on to Artificial Neural Networks (ANN). You will learn how to use different frameworks in Python to solve real-world problems using deep learning and artificial intelligence. Next, we will make predictions using linear regression, polynomial regression, and multivariate regression, and build artificial neural networks with TensorFlow and Keras. We will also cover Convolutional Neural Networks (CNN) at length and go through the different components such as convolution layer, pooling layer, and fully connected layer. Finally, we will wrap up the implementation of CNN in Python.

By the end of this course, you will be able to use the concepts of deep learning to build neural networks in python like a professional.

What You Will Learn

  • Learn the fundamentals of the deep learning theory
  • Learn how to use deep learning in Python
  • Learn how to use different frameworks in Python
  • Build artificial neural networks with TensorFlow and Keras
  • Learn implementation of ANN in Python
  • Learn implementation of CNN in Python


This course is intended for both beginners and professionals in programming who want to expand their knowledge of deep learning or professional mathematicians who want to learn how to analyze data programmatically. Basic mathematical skills and Python coding experience are prerequisites

About The Author

Meta Brains: Meta Brains is a team of passionate software developers and finance professionals. They provide professional training programs that combine their expertise in coding, finance, and Excel.

With a focus on the Metaverse, they aim to equip learners with the necessary skills to participate in the next computing revolution. Their inclusive approach ensures accessibility to everyone, fostering a community that collaboratively codes and builds the future of the Metaverse.

Table of contents

  1. Chapter 1 : Introduction to Deep Learning
    1. Course Introduction
    2. What is Deep Learning?
    3. Why is Deep Learning Important?
    4. Software and Frameworks
  2. Chapter 2 : Artificial Neural Networks (ANN)
    1. Section Introduction
    2. Anatomy and Function of Neurons
    3. An Introduction to The Neural Network
    4. Architecture of a Neural Network
  3. Chapter 3 : Propagation of Information in ANNs
    1. Feed-Forward and Back Propagation Networks
    2. Backpropagation in Neural Networks
    3. Minimizing the Cost Function Using Backpropagation
  4. Chapter 4 : Neural Network Architectures
    1. Single Layer Perceptron (SLP) Model
    2. Radial Basis Network (RBN)
    3. Multi-Layer Perceptron (MLP) Neural Network
    4. Recurrent Neural Network (RNN)
    5. Long Short-Term Memory (LSTM) Networks
    6. Hopfield Neural Network
    7. Boltzmann Machine Neural Network
  5. Chapter 5 : Activation Functions
    1. What is the Activation Function?
    2. Important Terminologies
    3. The Sigmoid Function
    4. Hyperbolic Tangent Function
    5. SoftMax Function
    6. Rectified Linear Unit (ReLU) Function
    7. Leaky Rectified Linear Unit function
  6. Chapter 6 : Gradient Descent Algorithm
    1. What is Gradient Descent?
    2. What is Stochastic Gradient Descent?
    3. Gradient Descent versus Stochastic Gradient Descent
  7. Chapter 7 : Summary - Overview of Neural Networks
    1. How do Artificial Neural Networks Work?
    2. Advantages of Neural Networks
    3. Disadvantages of Neural Networks
    4. Applications of Neural Networks
  8. Chapter 8 : Implementation of ANN in Python
    1. Introduction
    2. Exploring the Dataset
    3. Problem Statement
    4. Data Pre-Processing
    5. Loading the Dataset
    6. Splitting the Dataset into Independent and Dependent Variables
    7. Label Encoding Using Scikit-Learn
    8. One-hot encoding using scikit-learn
    9. Training and Test Sets: Splitting Data
    10. Feature Scaling
    11. Building the Artificial Neural Network
    12. Adding the Input Layer and the First Hidden Layer
    13. Adding the Next Hidden Layer
    14. Adding the Output Layer
    15. Compiling the Artificial Neural Network
    16. Fitting the ANN Model to the Training Set
    17. Predicting the Test Set Results
  9. Chapter 9 : Convolutional Neural Networks (CNN)
    1. Introduction
    2. Components of Convolutional Neural Networks
    3. Convolution Layer
    4. Pooling Layer
    5. Fully Connected Layer
  10. Chapter 10 : Implementation of CNN in Python
    1. Dataset
    2. Importing Libraries
    3. Building the CNN Model
    4. Accuracy of the Model

Product information

  • Title: Python for Deep Learning — Build Neural Networks in Python
  • Author(s): Meta Brains
  • Release date: August 2022
  • Publisher(s): Packt Publishing
  • ISBN: 9781804617878