Deep Learning with TensorFlow Online Course

Deep Learning with TensorFlow Online Course

TensorFlow, developed by Google, is the most widely used deep-learning library. It is a preferred tool for AI and machine learning applications. Mastering TensorFlow is essential for deep learning. This course teaches TensorFlow 2, starting with fundamental concepts like machine learning, classification, and regression. It then examines the link between artificial and biological neural networks, shaping deep learning principles. The final sections cover key loss functions and optimization methods such as gradient descent and Adam optimization. By the course’s end, learners will be equipped to build artificial neural networks using TensorFlow.

Who is this Course for?

This course is ideal for those interested in deep learning and machine learning, as well as anyone looking to implement deep neural networks using TensorFlow 2. It also serves as a foundation for advanced topics like convolutional neural networks, recurrent neural networks, LSTMs (Long Short-Term Memory), and transformers. A solid understanding of Python is required, along with familiarity with data science libraries like NumPy and Matplotlib.

What you will learn

• Understand machine learning fundamentals
• Build linear models using TensorFlow 2
• Develop deep neural networks with TensorFlow 2
• Perform image classification and regression
• Explore loss functions
• Learn optimization techniques

Course Table of Contents

Welcome

• Introduction
• Outline

Machine Learning and Neurons

• What is Machine Learning?
• Code Preparation (Classification Theory)
• Classification Notebook
• Code Preparation (Regression Theory)
• Regression Notebook
• The Neuron
• How Does a Model & Learn?
• Making Predictions
• Saving and Loading a Model
• Why Keras?
• Suggestion Box

Feedforward Artificial Neural Networks

• Artificial Neural Networks Section Introduction
• Forward Propagation
• The Geometrical Picture
• Activation Functions
• Multiclass Classification
• How to Represent Images
• Code Preparation (Artificial Neural Networks)
• ANN for Image Classification
• ANN for Regression
• How to Choose Hyperparameters

In-Depth: Loss Functions

• Mean Squared Error
• Binary Cross Entropy
• Categorical Cross Entropy

In-Depth: Gradient Descent

• Gradient Descent
• Stochastic Gradient Descent
• Momentum
• Variable and Adaptive Learning Rates
• Adam Optimization (Part 1)
• Adam Optimization (Part 2)