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

Die Lerneinheiten in dieser Liste gehören zum Kurs Applied Edge AI: Deep Learning Outside of the Cloud. Möchten Sie auf den gesamten Kursinhalt zugreifen?

Schreiben Sie sich hier ein

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!

Welcome to Week 1

Text

Course Start Survey

Umfrage

Course Introduction

Video

A Concise History of Neural Networks (1/4)

Video

A Concise History of Neural Networks (1/4)

Selbsttest

A Concise History of Neural Networks (2/4)

Video

A Concise History of Neural Networks (2/4)

Selbsttest

A Concise History of Neural Networks (3/4)

Video

A Concise History of Neural Networks (3/4)

Selbsttest

A Concise History of Neural Networks (4/4)

Video

A Concise History of Neural Networks (4/4)

Selbsttest

Stochastic Gradient Descent

Video

Stochastic Gradient Descent

Selbsttest

Computational Graph

Video

Computational Graph

Selbsttest

Convolutional Neural Networks

Video

Convolutional Neural Networks

Selbsttest

Learning Material

Text

Weekly Assignment

Benoteter Test

Practical Exercise Week 1 - LENGTH

Practical Exercise Quiz

Benoteter Test

Practical Exercise (Bonus)

Bonus-Test

Practical Exercise Week 1 - Solution

Text

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.

Welcome to Week 3

Text

Neural Network Compression

Video

Neural Network Compression

Selbsttest

Compact Network Design (1/3)

Video

Compact Network Design 1

Selbsttest

Compact Network Design (2/3)

Video

Compact Network Design 2

Selbsttest

Compact Network Design (3/3)

Video

Compact Network Design 3

Selbsttest

Knowledge Distillation (1/2)

Video

Knowledge Distillation 1

Selbsttest

Knowledge Distillation (2/2)

Video

Knowledge Distillation 2

Selbsttest

Learning Material

Text

Weekly Assignment

Benoteter Test

Practical Exercise Week 3 - Knowledge Distillation

Practical Exercise Quiz

Benoteter Test

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.

Welcome to Week 4

Text

Network Pruning

Video

Pruning

Selbsttest

Dynamic Network

Video

Dynamic Network

Selbsttest

Supernet-Subnets Architecture Search

Video

Supernet-subnets Architecture Search

Selbsttest

Neural Network Quantization

Video

Neural Network Quantization

Selbsttest

Binary Neural Networks (1/2)

Video

Binary Neural Networks 1

Selbsttest

Binary Neural Networks (2/2)

Video

Binary Neural Networks 2

Selbsttest

Learning Material

Text

Weekly Assignment

Benoteter Test

Practical Exercise Week 4 - Binary Neural Networks

Practical Exercise Quiz

Benoteter Test

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!

Welcome to Week 5

Text

Introduction of Edge AI

Video

Introduction of Edge AI

Selbsttest

Training and Inference

Video

Training and Inference

Selbsttest

Federated Learning (1/3)

Video

Federated Learning 1

Selbsttest

Federated Learning (2/3)

Video

Federated Learning 2

Selbsttest

Federated Learning (3/3)

Video

Federated Learning 3

Selbsttest

Learning Material

Text

Weekly Assignment

Benoteter Test

Practical Exercise Week 5 - Federated Learning

Practical Exercise Quiz

Benoteter Test

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.

Welcome to Week 6

Text

Edge AI Computing Model

Video

Edge AI Computing Model

Selbsttest

Advanced ML Methods for Edge AI (1/2)

Video

Advanced ML Methods for Edge AI 1

Selbsttest

Advanced ML Methods for Edge AI (2/2)

Video

Advanced ML Methods for Edge AI 2

Selbsttest

Edge AI Hardware

Video

Edge AI Hardware

Selbsttest

Edge AI Application Scenarios

Video

Application Scenarios

Selbsttest

Learning Material

Text

Weekly Assignment

Benoteter Test

Practical Exercise Week 6 - Collaborative Inference

Practical Exercise Quiz

Benoteter Test

Practical Exercise Week 6 - Solution

Text

Week 7 - Final Exam

Final Exam

Text

Final exam

Benoteter Test

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