Description

In this self-paced course, you will learn how to use TensorFlow 2 to build deep neural networks. You will learn the basics of machine learning, classification, and regression. We will also discuss the connection between artificial and biological neural networks and how that inspires our thinking in deep learning.

TensorFlow is the world's most popular library for deep learning, and it is built by Google. It is the library of choice for many companies doing AI and machine learning. So, if you want to do deep learning, you got to know TensorFlow. In this course, you will learn how to use TensorFlow 2 to build deep neural networks. We will first start by learning the basics of machine learning, classification, and regression. Then in the next section, we will understand the connection between artificial neural networks and biological neural networks and how that inspires our thinking in the field of deep learning. In the last two sections, you will learn about loss functions to understand mean squared error, binary cross entropy, and categorical cross entropy and gradient descent to understand stochastic gradient descent, momentum, variable and adaptive learning rates, and Adam optimization. By the end of this course, we will have understood how to use TensorFlow for artificial neural networks in deep learning.

What You Will Learn

Understand what machine learning is
Build linear models with TensorFlow 2
Learn how to build deep neural networks with TensorFlow 2
Learn how to perform image classification and regression with ANN
Learn loss functions such as mean-squared error and cross-entropy loss
Learn about stochastic gradient descent, momentum, and Adam optimization

Audience

This course is designed for anyone interested in deep learning and machine learning, anyone who wants to implement deep neural networks in TensorFlow 2, or anyone interested in building a foundation for convolutional neural networks, recurrent neural networks, LSTMs (Long Short Term Memory), and transformers.

One must have decent Python programming skills and should be comfortable with data science libraries such as NumPy and Matplotlib.

Approach

In this self-paced course, you will learn how to use TensorFlow 2 to build artificial neural networks. The course is well-balanced with theory that explains the ANN concepts and hands-on coding exercises for practical understanding.

Key Features

Understand the utilization of TensorFlow 2 to construct artificial neural networks * The course covers the basics of machine learning, classification, and regression * Explore the connection between artificial neural networks and biological neural networks

About the Author

Lazy Programmer

The Lazy Programmer, a distinguished online educator, boasts dual master's degrees in computer engineering and statistics, with a decade-long specialization in machine learning, pattern recognition, and deep learning, where he authored pioneering courses. His professional journey includes enhancing online advertising and digital media, notably increasing click-through rates and revenue. As a versatile full-stack software engineer, he excels in Python, Ruby on Rails, C++, and more. His expansive knowledge covers areas like bioinformatics and algorithmic trading, showcasing his diverse skill set. Dedicated to simplifying complex topics, he stands as a pivotal figure in online education, adeptly navigating students through the nuances of data science and AI.

Course Outline

1. Welcome

1. Introduction

In this video, we will introduce the author and understand the course learning objective.

1. Introduction

In this video, we will introduce the author and understand the course learning objective.

2. Outline

In this video, we will understand the course learning approach and what is required to start with this course. Then we will also understand what is covered in this course.

2. Outline

In this video, we will understand the course learning approach and what is required to start with this course. Then we will also understand what is covered in this course.

2. Machine Learning and Neurons

In this section, we will cover a crash course on machine learning and neurons. You will learn about classification and regression, and their TensorFlow implementations.

1. What Is Machine Learning?

In this video, we will understand what machine learning is and get a clear idea about ML (machine learning).

2. Code Preparation (Classification Theory)

In this video, we will take a crash course in linear classification for TensorFlow 2.0.

3. Classification Notebook

In this video, we will understand linear classification with the help of breast cancer dataset example.

4. Code Preparation (Regression Theory)

In this video, we will take a crash course in linear regression for TensorFlow 2.0.

5. Regression Notebook

In this video, we will understand linear regression by proving the Mosse law true.

6. The Neuron

In this video, we will understand the neuron.

7. How Does a Model 'Learn'?

In this video, we will understand how a model 'learns'.

8. Making Predictions

In this video, we will be talking about another important part of creating a model, which is making predictions.

9. Saving and Loading a Model

In this video, you will learn how to save a model and then load it later.

10. Why Keras?

In this video, we will understand why we use Keras in this course and not TensorFlow 2.

11. Suggestion Box

In this video, we will have a look at the suggestion box where we can add feedback for this course.

3. Feedforward Artificial Neural Networks

In this section, we will cover feedforward artificial neural networks.

1. Artificial Neural Networks Section Introduction

In this video, we will get introduced to artificial neural networks.

2. Forward Propagation

In this video, you will learn about forward propagation as it is related to neural networks.

3. The Geometrical Picture

In this video, we will understand the geometrical picture by understanding why neural networks are so important instead of a single neural network.

4. Activation Functions

In this video, you will learn about activation functions.

5. Multiclass Classification

In this video, you will learn about multiclass classification.

6. How to Represent Images

In this video, we will discuss data and understand how to represent images.

7. Code Preparation (Artificial Neural Networks)

In this video, we will work with the MNIST dataset and ANN code preparation.

8. ANN for Image Classification

In this video, we will work on image classification with the MNIST dataset.

9. ANN for Regression

In this video, we will understand regression in ANN.

10. How to Choose Hyperparameters

In this video, we will understand how to choose hyperparameters.

4. In-Depth: Loss Functions

In this optional section, we will dive deeper into loss functions.

1. Mean Squared Error

In this video, we will understand MSE (Mean Squared Error) from a probabilistic perspective.

2. Binary Cross Entropy

In this video, you will learn about binary cross entropy, which is the correct loss function to use for binary classification.

3. Categorical Cross Entropy

In this video, you will learn about categorical cross entropy, which is used in multiclass classification.

5. In-Depth: Gradient Descent

In this optional section, we will dive deeper into gradient descent.

1. Gradient Descent

In this video, we will get introduced to gradient descent.

2. Stochastic Gradient Descent

In this video, you will learn about stochastic gradient descent.

3. Momentum

In this video, you will learn about momentum.

4. Variable and Adaptive Learning Rates

In this video, we will discuss variable and adaptive learning rates.

5. Adam Optimization (Part 1)

In this video, we will talk about Adam optimization, get introduced to Adam, and understand its basics.

6. Adam Optimization (Part 2)

In this video, we will understand more about Adam optimization.

Course Images

Deep Learning - Artificial Neural Networks with TensorFlow

By Packt

Booking options

Highlights