Deep Learning: Getting Started (2021)

Course details

Deep learning as a technology has grown leaps and bounds in the last few years. More and more AI solutions use deep learning as their foundational technology. Studying this technology, however, has several challenges. Most learning resources are math-heavy and are difficult to navigate without good math skills. IT professionals need a simplified resource to learn the concepts and build models quickly. This course aims to provide a simplified path to studying the basics of deep learning and becoming productive quickly. Instructor Kumaran Ponnambalam starts off with an intro to deep learning, including artificial neural networks and architectures. He navigates through various building blocks of neural networks with simple and easy to understand explanations. Kumaran also builds code in Keras to implement these building blocks. He then pulls it all together with an end-to-end exercise. Finally, test what you learned with a deep learning problem and compare your solution with Kumaran’s.

Concepts

Introduction

Getting started with deep learning
Prerequisites for the course
Setting up the environment

Introduction to Deep Learning

What is deep learning
Linear regression
An analogy for deep learning
The perceptron
Artificial neural networks
Training an ANN

Neural Network Architecture

The input layer
Hidden layers
Weights and biases
Activation functions
The output layer

Deep Learning Example 1

The Iris classification problem
Input preprocessing
Creating a deep learning model
Training and evaluation
Saving and loading models
Predictions with deep learning models

Deep Learning Example 2

Spam classification problem
Creating text representations
Building a spam model
Predictions for text

Deep Learning Exercise

Exercise problem statement
Preprocessing RCA data
Building the RCA model
Predicting root causes with deep learning

Conclusion

Extending your deep learning education