Overview | Applied Edge AI: Deep Learning Outside of the Cloud

The listed learning units belong to the course Applied Edge AI: Deep Learning Outside of the Cloud. Do you want to access all course content?

Enroll yourself

Week 1 - Basics and History of Neural Networks

In this week, we provide you with a concise history of neural networks to learn about how the field of deep learning evolved and what challenges have been overcome. Furthermore, we provide you with some basic knowledge about the learning process of deep neural networks. We will also have a practical session, where you are going to implement a few basic neural network layers from scratch!

A Concise History of Neural Networks (1/4)

Learning materials

Welcome to Week 1

Text

A Concise History of Neural Networks (2/4)

Learning materials

Course Start Survey

Survey

A Concise History of Neural Networks (3/4)

Learning materials

A Concise History of Neural Networks (4/4)

Learning materials

Self-Reflection Questionnaire

Survey

Stochastic Gradient Descent

Learning materials

Computational Graph

Learning materials

Convolutional Neural Networks

Learning materials

Self-Reflection Questionnaire

Survey

Course Introduction

Video

A Concise History of Neural Networks (1/4)

Video

A Concise History of Neural Networks (2/4)

Video

A Concise History of Neural Networks (3/4)

Video

A Concise History of Neural Networks (4/4)

Video

Stochastic Gradient Descent

Video

Computational Graph

Video

Convolutional Neural Networks

Video

Learning Material

Text

Weekly Assignment

Learning materials

Practical Exercise Week 1 - LENGTH

Text

Practical Exercise Quiz

Learning materials

Practical Exercise (Bonus)

Learning materials

Practical Exercise Week 1 - Solution

Text

Self-Reflection Questionnaire

Survey

Self-Reflection Questionnaire

Survey

Week 2 - CNN Architectures

Over time it has been found that specific architectures for neural networks achieve the best results. In this week, we provide you with an extensive overview of neural architectures for image classification and how they evolved over time. In the practical session, we will use PyTorch to train a neural network for image classification on the CIFAR-100 dataset.

Week 3 - Compact Network Design and Knowledge Distillation

In this week, you will learn all about the design of compact neural networks and knowledge distillation. Both methods are of high importance when applying deep neural networks on edge devices because they reduce the memory, computation, and energy requirements of neural networks! In the practical session, we will implement and experiment with knowledge distillation on the CIFAR-100 dataset.

Neural Network Compression

Learning materials

Compact Network Design 1

Learning materials

Welcome to Week 3

Text

Neural Network Compression

Video

Compact Network Design 2

Learning materials

Compact Network Design (1/3)

Video

Compact Network Design 3

Learning materials

Compact Network Design (2/3)

Video

Knowledge Distillation 1

Learning materials

Compact Network Design (3/3)

Video

Knowledge Distillation 2

Learning materials

Knowledge Distillation (1/2)

Video

Weekly Assignment

Learning materials

Knowledge Distillation (2/2)

Video

Learning Material

Text

Practical Exercise Week 3 - Knowledge Distillation

Text

Practical Exercise Quiz

Learning materials

Practical Exercise Week 3 - Solution

Text

Week 4 - Advanced Deep Compression Methods

In this week, we will investigate further model compression techniques, such as pruning, dynamic networks, and network quantization. The practical session of this week is all about the training of a binary neural network on the CIFAR-100 dataset.

Pruning

Learning materials

Dynamic Network

Learning materials

Supernet-subnets Architecture Search

Learning materials

Welcome to Week 4

Text

Supernet-Subnets Architecture Search

Video

Network Pruning

Video

Neural Network Quantization

Learning materials

Dynamic Network

Video

Binary Neural Networks 1

Learning materials

Binary Neural Networks 2

Learning materials

Neural Network Quantization

Video

Weekly Assignment

Learning materials

Binary Neural Networks (1/2)

Video

Binary Neural Networks (2/2)

Video

Learning Material

Text

Practical Exercise Week 4 - Binary Neural Networks

Text

Practical Exercise Quiz

Learning materials

Practical Exercise Week 4 - Solution

Text

Week 5 - Edge AI Introduction and Federated Learning

In this week, we will perform a deep dive into federated learning. A technique that allows to decentralize the training of a neural network. Such a decentralized training has many advantages, e.g., we do not need to copy the data between hosts and can train directly on an edge device! This weeks practical session is as much an experiment for you as it is for us! Together with all other course participants you will train a model for image classification on the ImageNet dataset in a decentralized manner!

Introduction of Edge AI

Learning materials

Training and Inference

Learning materials

Federated Learning 1

Learning materials

Federated Learning 2

Learning materials

Introduction of Edge AI

Video

Welcome to Week 5

Text

Federated Learning 3

Learning materials

Training and Inference

Video

Weekly Assignment

Learning materials

Federated Learning (1/3)

Video

Federated Learning (2/3)

Video

Federated Learning (3/3)

Video

Learning Material

Text

Practical Exercise Week 5 - Federated Learning

Text

Practical Exercise Quiz

Learning materials

Practical Exercise Week 5 - Solution

Text

Week 6 - Edge AI Concepts

In this week, we will have a look at further advanced concepts behind Edge AI, we will also investigate specific Edge AI hardware and application scenarios. In the practical session, you will experiment with a collaborative inference task, where edge devices and cloud devices work together.

Edge AI Computing Model

Learning materials

Advanced ML Methods for Edge AI 1

Learning materials

Advanced ML Methods for Edge AI 2

Learning materials

Edge AI Hardware

Learning materials

Welcome to Week 6

Text

Application Scenarios

Learning materials

Edge AI Computing Model

Video

Advanced ML Methods for Edge AI (1/2)

Video

Weekly Assignment

Learning materials

Advanced ML Methods for Edge AI (2/2)

Video

Edge AI Hardware

Video

Edge AI Application Scenarios

Video

Learning Material

Text

Practical Exercise Week 6 - Collaborative Inference

Text

Practical Exercise Quiz

Learning materials

Practical Exercise Week 6 - Solution

Text

Week 7 - Final Exam

Final Exam

Text

Final exam

Learning materials

I like, I wish

After the course is finished, we would like to gather your feedback in an optional survey.

I like, I wish - what is that?

Text

Go to overview

Week 1 - Basics and History of Neural Networks
- A Concise History of Neural Networks (1/4)
- Welcome to Week 1
- A Concise History of Neural Networks (2/4)
- Course Start Survey
- A Concise History of Neural Networks (3/4)
- A Concise History of Neural Networks (4/4)
- Self-Reflection Questionnaire
- Stochastic Gradient Descent
- Computational Graph
- Convolutional Neural Networks
- Self-Reflection Questionnaire
- Course Introduction
- A Concise History of Neural Networks (1/4)
- A Concise History of Neural Networks (2/4)
- A Concise History of Neural Networks (3/4)
- A Concise History of Neural Networks (4/4)
- Stochastic Gradient Descent
- Computational Graph
- Convolutional Neural Networks
- Learning Material
- Weekly Assignment
- Practical Exercise Week 1 - LENGTH
- Practical Exercise Quiz
- Practical Exercise (Bonus)
- Practical Exercise Week 1 - Solution
- Self-Reflection Questionnaire
- Self-Reflection Questionnaire
Week 2 - CNN Architectures
- Welcome to Week 2
- Self-Reflection Questionnaire
- Self-Reflection Questionnaire
- CNN Architectures (1/6)
- CNN Architectures (1/6)
- CNN Architectures (2/6)
- CNN Architectures (2/6)
- CNN Architectures (3/6)
- CNN Architectures (3/6)
- CNN Architectures (4/6)
- CNN Architectures (4/6)
- CNN Architectures (5/6)
- CNN Architectures (5/6)
- CNN Architectures (6/6)
- CNN Architectures (6/6)
- Transformer
- Transformer
- Learning Material
- Weekly Assignment
- Practical Exercise Week 2 - CIFAR 100
- Practical Exercise Quiz
- Practical Exercise Week 2 - Solution
- Self-Reflection Questionnaire
- Self-Reflection Questionnaire
Week 3 - Compact Network Design and Knowledge Distillation
- Neural Network Compression
- Compact Network Design 1
- Welcome to Week 3
- Neural Network Compression
- Compact Network Design 2
- Compact Network Design (1/3)
- Compact Network Design 3
- Compact Network Design (2/3)
- Knowledge Distillation 1
- Compact Network Design (3/3)
- Knowledge Distillation 2
- Knowledge Distillation (1/2)
- Weekly Assignment
- Knowledge Distillation (2/2)
- Learning Material
- Practical Exercise Week 3 - Knowledge Distillation
- Practical Exercise Quiz
- Practical Exercise Week 3 - Solution
Week 4 - Advanced Deep Compression Methods
- Pruning
- Dynamic Network
- Supernet-subnets Architecture Search
- Welcome to Week 4
- Supernet-Subnets Architecture Search
- Network Pruning
- Neural Network Quantization
- Dynamic Network
- Binary Neural Networks 1
- Binary Neural Networks 2
- Neural Network Quantization
- Weekly Assignment
- Binary Neural Networks (1/2)
- Binary Neural Networks (2/2)
- Learning Material
- Practical Exercise Week 4 - Binary Neural Networks
- Practical Exercise Quiz
- Practical Exercise Week 4 - Solution
Week 5 - Edge AI Introduction and Federated Learning
- Introduction of Edge AI
- Training and Inference
- Federated Learning 1
- Federated Learning 2
- Introduction of Edge AI
- Welcome to Week 5
- Federated Learning 3
- Training and Inference
- Weekly Assignment
- Federated Learning (1/3)
- Federated Learning (2/3)
- Federated Learning (3/3)
- Learning Material
- Practical Exercise Week 5 - Federated Learning
- Practical Exercise Quiz
- Practical Exercise Week 5 - Solution
Week 6 - Edge AI Concepts
- Edge AI Computing Model
- Advanced ML Methods for Edge AI 1
- Advanced ML Methods for Edge AI 2
- Edge AI Hardware
- Welcome to Week 6
- Application Scenarios
- Edge AI Computing Model
- Advanced ML Methods for Edge AI (1/2)
- Weekly Assignment
- Advanced ML Methods for Edge AI (2/2)
- Edge AI Hardware
- Edge AI Application Scenarios
- Learning Material
- Practical Exercise Week 6 - Collaborative Inference
- Practical Exercise Quiz
- Practical Exercise Week 6 - Solution
Week 7 - Final Exam
- Final Exam
- Final exam
I like, I wish
- I like, I wish - what is that?