Курс із самостійним навчанням

Applied Edge AI: Deep Learning Outside of the Cloud

Запропоновано PD Dr. Haojin Yang, Joseph Bethge (Teaching Team)

Перераховані навчальні одиниці належать до курсу Applied Edge AI: Deep Learning Outside of the Cloud. Бажаєте отримати доступ до всього вмісту курсу?

Запишіться самі

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

Текст

Course Start Survey

Опитування

Course Introduction

Відео

A Concise History of Neural Networks (1/4)

Відео

A Concise History of Neural Networks (1/4)

Самоперевірка

A Concise History of Neural Networks (2/4)

Відео

A Concise History of Neural Networks (2/4)

Самоперевірка

A Concise History of Neural Networks (3/4)

Відео

A Concise History of Neural Networks (3/4)

Самоперевірка

A Concise History of Neural Networks (4/4)

Відео

A Concise History of Neural Networks (4/4)

Самоперевірка

Stochastic Gradient Descent

Відео

Stochastic Gradient Descent

Самоперевірка

Computational Graph

Відео

Computational Graph

Самоперевірка

Convolutional Neural Networks

Відео

Convolutional Neural Networks

Самоперевірка

Learning Material

Текст

Weekly Assignment

Оцінюваний тест

Practical Exercise Week 1 - LENGTH

Practical Exercise Quiz

Оцінюваний тест

Practical Exercise (Bonus)

Бонусний тест

Practical Exercise Week 1 - Solution

Текст

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.

Welcome to Week 2

Текст

CNN Architectures (1/6)

Відео

CNN Architectures (1/6)

Самоперевірка

CNN Architectures (2/6)

Відео

CNN Architectures (2/6)

Самоперевірка

CNN Architectures (3/6)

Відео

CNN Architectures (3/6)

Самоперевірка

CNN Architectures (4/6)

Відео

CNN Architectures (4/6)

Самоперевірка

CNN Architectures (5/6)

Відео

CNN Architectures (5/6)

Самоперевірка

CNN Architectures (6/6)

Відео

CNN Architectures (6/6)

Самоперевірка

Transformer

Відео

Transformer

Самоперевірка

Learning Material

Текст

Weekly Assignment

Оцінюваний тест

Practical Exercise Week 2 - CIFAR 100

Practical Exercise Quiz

Оцінюваний тест

Practical Exercise Week 2 - Solution

Текст

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

Текст

Neural Network Compression

Відео

Neural Network Compression

Самоперевірка

Compact Network Design (1/3)

Відео

Compact Network Design 1

Самоперевірка

Compact Network Design (2/3)

Відео

Compact Network Design 2

Самоперевірка

Compact Network Design (3/3)

Відео

Compact Network Design 3

Самоперевірка

Knowledge Distillation (1/2)

Відео

Knowledge Distillation 1

Самоперевірка

Knowledge Distillation (2/2)

Відео

Knowledge Distillation 2

Самоперевірка

Learning Material

Текст

Weekly Assignment

Оцінюваний тест

Practical Exercise Week 3 - Knowledge Distillation

Practical Exercise Quiz

Оцінюваний тест

Practical Exercise Week 3 - Solution

Текст

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

Текст

Network Pruning

Відео

Pruning

Самоперевірка

Dynamic Network

Відео

Dynamic Network

Самоперевірка

Supernet-Subnets Architecture Search

Відео

Supernet-subnets Architecture Search

Самоперевірка

Neural Network Quantization

Відео

Neural Network Quantization

Самоперевірка

Binary Neural Networks (1/2)

Відео

Binary Neural Networks 1

Самоперевірка

Binary Neural Networks (2/2)

Відео

Binary Neural Networks 2

Самоперевірка

Learning Material

Текст

Weekly Assignment

Оцінюваний тест

Practical Exercise Week 4 - Binary Neural Networks

Practical Exercise Quiz

Оцінюваний тест

Practical Exercise Week 4 - Solution

Текст

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

Текст

Introduction of Edge AI

Відео

Introduction of Edge AI

Самоперевірка

Training and Inference

Відео

Training and Inference

Самоперевірка

Federated Learning (1/3)

Відео

Federated Learning 1

Самоперевірка

Federated Learning (2/3)

Відео

Federated Learning 2

Самоперевірка

Federated Learning (3/3)

Відео

Federated Learning 3

Самоперевірка

Learning Material

Текст

Weekly Assignment

Оцінюваний тест

Practical Exercise Week 5 - Federated Learning

Practical Exercise Quiz

Оцінюваний тест

Practical Exercise Week 5 - Solution

Текст

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

Текст

Edge AI Computing Model

Відео

Edge AI Computing Model

Самоперевірка

Advanced ML Methods for Edge AI (1/2)

Відео

Advanced ML Methods for Edge AI 1

Самоперевірка

Advanced ML Methods for Edge AI (2/2)

Відео

Advanced ML Methods for Edge AI 2

Самоперевірка

Edge AI Hardware

Відео

Edge AI Hardware

Самоперевірка

Edge AI Application Scenarios

Відео

Application Scenarios

Самоперевірка

Learning Material

Текст

Weekly Assignment

Оцінюваний тест

Practical Exercise Week 6 - Collaborative Inference

Practical Exercise Quiz

Оцінюваний тест

Practical Exercise Week 6 - Solution

Текст

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?

Текст