Deep Learning - Deep Neural Network for Beginners Using Python

Deep Learning - Deep Neural Network for Beginners Using Python

by AI Sciences
Released January 2023
Publisher(s): Packt Publishing
ISBN: 9781837633579

Watch 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

Are you ready to start your path to becoming a deep learning expert? Then this course is for you.

This course is step-by-step. In every new tutorial, we build on what we have already learned and move one extra step forward, and then we assign you a small task that is solved at the beginning of the next video. We start by teaching the theoretical part of the concept, and then implement everything as it is practically using Python.

This comprehensive course will be your guide to learning how to use the power of Python to train your machine such that your machine starts learning just like humans, and based on that learning, your machine starts making predictions as well!

We will be using Python as a programming language in this course, which is the hottest language nowadays if we talk about machine learning. Python will be taught from the elementary level up to an advanced level so that any machine learning concept can be implemented.

You will also learn various steps of data preprocessing, which allows us to make data ready for machine learning algorithms.

You will learn the general concepts of machine learning overall, which will be followed by the implementation of one of the essential ML algorithms, “Deep Neural Networks”. Each concept of DNNs will be taught theoretically and will be implemented using Python.

By the end of this course, you will be able to understand the methodology of DNNs with deep learning using real-world datasets.

What You Will Learn

  • Learn the basics of machine learning and neural networks
  • Understand the architecture of neural networks
  • Learn the basics of training a DNN using the Gradient Descent algorithm
  • Learn how to implement a complete DNN using NumPy
  • Learn to create a complete structure for DNN from scratch using Python
  • Work on a project using deep learning for the IRIS dataset

Audience

This course is designed for anyone who is interested in data science or interested in taking their data-speak to a higher level.

Students who want to master DNNs with real datasets in deep learning or who want to implement DNNs in realistic projects can also benefit from the course. You need to have a background in deep learning to get the best out of this course.

About The Author

AI Sciences: AI Sciences is a group of experts, PhDs, and practitioners of AI, ML, computer science, and statistics. Some of the experts work in big companies such as Amazon, Google, Facebook, Microsoft, KPMG, BCG, and IBM.

They have produced a series of courses mainly dedicated to beginners and newcomers on the techniques and methods of machine learning, statistics, artificial intelligence, and data science.

Initially, their objective was to help only those who wish to understand these techniques more easily and to be able to start without too much theory. Today, they also publish more complete courses for a wider audience. Their courses have had phenomenal success and have helped more than 100,000 students master AI and data science.

Table of contents

  1. Chapter 1 : Introduction
    1. Course Promo
    2. Introduction to Instructor
    3. Introduction to Course
  2. Chapter 2 : Basics of Deep Learning
    1. Problem to Solve Part 1
    2. Problem to Solve Part 2
    3. Problem to Solve Part 3
    4. Linear Equation
    5. Linear Equation Vectorized
    6. 3D Feature Space
    7. N-Dimensional Space
    8. Theory of Perceptron
    9. Implementing Basic Perceptron
    10. Logical Gates for Perceptrons
    11. Perceptron Training Part 1
    12. Perceptron Training Part 2
    13. Learning Rate
    14. Perceptron Training Part 3
    15. Perceptron Algorithm
    16. Coding Perceptron Algo (Data Reading and Visualization)
    17. Coding Perceptron Algo (Perceptron Step)
    18. Coding Perceptron Algo (Training Perceptron)
    19. Coding Perceptron Algo (Visualizing the Results)
    20. Problem with Linear Solutions
    21. Solution to Problem
    22. Error Functions
    23. Discrete Versus Continuous Error Function
    24. Sigmoid Function
    25. Multi-Class Problem
    26. Problem of Negative Scores
    27. Need of SoftMax
    28. Coding SoftMax
    29. One-Hot Encoding
    30. Maximum Likelihood Part 1
    31. Maximum Likelihood Part 2
    32. Cross Entropy
    33. Cross Entropy Formulation
    34. Multi-Class Cross Entropy
    35. Cross Entropy Implementation
    36. Sigmoid Function Implementation
    37. Output Function Implementation
  3. Chapter 3 : Deep Learning
    1. Introduction to Gradient Descent
    2. Convex Functions
    3. Use of Derivatives
    4. How Gradient Descent Works
    5. Gradient Step
    6. Logistic Regression Algorithm
    7. Data Visualization and Reading
    8. Updating Weights in Python
    9. Implementing Logistic Regression
    10. Visualization and Results
    11. Gradient Descent Versus Perceptron
    12. Linear to Non-Linear Boundaries
    13. Combining Probabilities
    14. Weighted Sums
    15. Neural Network Architecture
    16. Layers and DEEP Networks
    17. Multi-Class Classification
    18. Basics of Feed Forward
    19. Feed Forward for DEEP Net
    20. Deep Learning Algo Overview
    21. Basics of Backpropagation
    22. Updating Weights
    23. Chain Rule for Backpropagation
    24. Sigma Prime
    25. Data Analysis NN (Neural Networks) Implementation
    26. One-Hot Encoding (NN Implementation)
    27. Scaling the Data (NN Implementation)
    28. Splitting the Data (NN Implementation)
    29. Helper Functions (NN Implementation)
    30. Training (NN Implementation)
    31. Testing (NN Implementation)
  4. Chapter 4 : Optimizations
    1. Underfitting vs Overfitting
    2. Early Stopping
    3. Quiz
    4. Solution and Regularization
    5. L1 and L2 Regularization
    6. Dropout
    7. Local Minima Problem
    8. Random Restart Solution
    9. Vanishing Gradient Problem
    10. Other Activation Functions
  5. Chapter 5 : Final Project
    1. Final Project Part 1
    2. Final Project Part 2
    3. Final Project Part 3
    4. Final Project Part 4
    5. Final Project Part 5

Product information

  • Title: Deep Learning - Deep Neural Network for Beginners Using Python
  • Author(s): AI Sciences
  • Release date: January 2023
  • Publisher(s): Packt Publishing
  • ISBN: 9781837633579