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

列出的学习单元属于课程Applied Edge AI: Deep Learning Outside of the Cloud。您想访问所有课程内容吗？

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

文本

Course Start Survey

调查

Course Introduction

视频

A Concise History of Neural Networks (1/4)

视频

A Concise History of Neural Networks (1/4)

自我测试

A Concise History of Neural Networks (2/4)

视频

A Concise History of Neural Networks (2/4)

自我测试

A Concise History of Neural Networks (3/4)

视频

A Concise History of Neural Networks (3/4)

自我测试

A Concise History of Neural Networks (4/4)

视频

A Concise History of Neural Networks (4/4)

自我测试

Stochastic Gradient Descent

视频

Stochastic Gradient Descent

自我测试

Computational Graph

视频

Computational Graph

自我测试

Convolutional Neural Networks

视频

Convolutional Neural Networks

自我测试

Learning Material

文本

Weekly Assignment

分级测试

Practical Exercise Week 1 - LENGTH

Practical Exercise Quiz

分级测试

Practical Exercise (Bonus)

奖励测试

Practical Exercise Week 1 - Solution

文本

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

文本

Neural Network Compression

视频

Neural Network Compression

自我测试

Compact Network Design (1/3)

视频

Compact Network Design 1

自我测试

Compact Network Design (2/3)

视频

Compact Network Design 2

自我测试

Compact Network Design (3/3)

视频

Compact Network Design 3

自我测试

Knowledge Distillation (1/2)

视频

Knowledge Distillation 1

自我测试

Knowledge Distillation (2/2)

视频

Knowledge Distillation 2

自我测试

Learning Material

文本

Weekly Assignment

分级测试

Practical Exercise Week 3 - Knowledge Distillation

Practical Exercise Quiz

分级测试

Practical Exercise Week 3 - Solution

文本

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

文本

Network Pruning

视频

Pruning

自我测试

Dynamic Network

视频

Dynamic Network

自我测试

Supernet-Subnets Architecture Search

视频

Supernet-subnets Architecture Search

自我测试

Neural Network Quantization

视频

Neural Network Quantization

自我测试

Binary Neural Networks (1/2)

视频

Binary Neural Networks 1

自我测试

Binary Neural Networks (2/2)

视频

Binary Neural Networks 2

自我测试

Learning Material

文本

Weekly Assignment

分级测试

Practical Exercise Week 4 - Binary Neural Networks

Practical Exercise Quiz

分级测试

Practical Exercise Week 4 - Solution

文本

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

文本

Introduction of Edge AI

视频

Introduction of Edge AI

自我测试

Training and Inference

视频

Training and Inference

自我测试

Federated Learning (1/3)

视频

Federated Learning 1

自我测试

Federated Learning (2/3)

视频

Federated Learning 2

自我测试

Federated Learning (3/3)

视频

Federated Learning 3

自我测试

Learning Material

文本

Weekly Assignment

分级测试

Practical Exercise Week 5 - Federated Learning

Practical Exercise Quiz

分级测试

Practical Exercise Week 5 - Solution

文本

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

文本

Edge AI Computing Model

视频

Edge AI Computing Model

自我测试

Advanced ML Methods for Edge AI (1/2)

视频

Advanced ML Methods for Edge AI 1

自我测试

Advanced ML Methods for Edge AI (2/2)

视频

Advanced ML Methods for Edge AI 2

自我测试

Edge AI Hardware

视频

Edge AI Hardware

自我测试

Edge AI Application Scenarios

视频

Application Scenarios

自我测试

Learning Material

文本

Weekly Assignment

分级测试

Practical Exercise Week 6 - Collaborative Inference

Practical Exercise Quiz

分级测试

Practical Exercise Week 6 - Solution

文本

Week 7 - Final Exam

Final Exam

文本

Final exam

分级测试

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?

文本