Introduction to Deep Learning

This is a hands-on introduction to the first steps in deep learning, intended for researchers who are familiar with (non-deep) machine learning.

The use of deep learning has seen a sharp increase of popularity and applicability over the last decade. While deep learning can be a useful tool for researchers from a wide range of domains, taking the first steps in the world of deep learning can be somewhat intimidating. This introduction covers the basics of deep learning in a practical and hands-on manner, so that upon completion, you will be able to train your first neural network and understand what next steps to take to improve the model.

We start with explaining the basic concepts of neural networks, and then go through the different steps of a deep learning workflow. Learners will learn how to prepare data for deep learning, how to implement a basic deep learning model in Python with Keras, how to monitor and troubleshoot the training process and how to implement different layer types such as convolutional layers.

Preparation

• Setup

The lesson

• 1. Introduction
• 2. Classification by a neural network using Keras
• 3. Monitor the training process
• 4. Advanced layer types
• 5. Transfer learning
• 6. Outlook

Reference

• Reference for learners
• Instructor notes
• Learner profiles

Schedule

Day 1

Time	Topic
9:00	Welcome and Icebreaker
9:10	Introduction to Deep Learning
9:50	Coffee Break
10:00	Classification by a neural network using Keras
10:50	Coffee Break
11:00	Classification by a neural network using Keras
11:50	Wrap-up
12:00	END

Day 2

Time	Topic
9:00	Welcome and recap
9:10	Monitor the training process
9:50	Coffee Break
10:00	Monitor the training process
10:20	Advanced Layer Types
10:50	Coffee Break
11:00	Advanced Layer Types
11:20	Transfer learning
11:40	Outlook
11:50	Wrap-up
12:00	END

Day 3

Time	Topic
9:00	Welcome and recap
9:05	TBD
9:55	Coffee Break
10:00	TBD
10:50	Coffee Break
11:00	TBD
11:50	Post-workshop survey
12:00	END

Other related lessons

Original carpentries lesson

This lesson is an adaptation of https://carpentries-lab.github.io/deep-learning-intro, licensed CC-BY-4.0.

Introduction to artificial neural networks in Python

The Introduction to artificial neural networks in Python lesson takes a different angle to introducing deep learning, focusing on computer vision with the application on medical images.

Introduction to machine learning in Python with scikit-learn

The Introduction to machine learning in Python with scikit-learn lesson introduces practical machine learning using Python. It is a good lesson to follow in preparation for this lesson, since basic knowledge of machine learning and Python programming skills are required for this lesson.

Prerequisites

Learners are expected to have the following knowledge:

• Basic Python programming skills and familiarity with the Pandas package.

• Basic knowledge on machine learning, including the following concepts: Data cleaning, train & test split, type of problems (regression, classification), overfitting & underfitting, metrics (accuracy, recall, etc.).