Applied Edge AI: Deep Learning Outside of the CloudPD Dr. Haojin Yang, Joseph Bethge (Teaching Team)

Las unidades de aprendizaje listadas pertenecen al curso Applied Edge AI: Deep Learning Outside of the Cloud. ¿Desea acceder a todo el contenido del curso?

Inscríbase usted mismo

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

Texto

Course Start Survey

Encuesta

Course Introduction

Vídeo

A Concise History of Neural Networks (1/4)

Vídeo

A Concise History of Neural Networks (1/4)

Prueba de autoevaluación

A Concise History of Neural Networks (2/4)

Vídeo

A Concise History of Neural Networks (2/4)

Prueba de autoevaluación

A Concise History of Neural Networks (3/4)

Vídeo

A Concise History of Neural Networks (3/4)

Prueba de autoevaluación

A Concise History of Neural Networks (4/4)

Vídeo

A Concise History of Neural Networks (4/4)

Prueba de autoevaluación

Stochastic Gradient Descent

Vídeo

Stochastic Gradient Descent

Prueba de autoevaluación

Computational Graph

Vídeo

Computational Graph

Prueba de autoevaluación

Convolutional Neural Networks

Vídeo

Convolutional Neural Networks

Prueba de autoevaluación

Learning Material

Texto

Weekly Assignment

Prueba evaluada

Practical Exercise Week 1 - LENGTH

Practical Exercise Quiz

Prueba evaluada

Practical Exercise (Bonus)

Prueba (bonus)

Practical Exercise Week 1 - Solution

Texto

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

Texto

CNN Architectures (1/6)

Vídeo

CNN Architectures (1/6)

Prueba de autoevaluación

CNN Architectures (2/6)

Vídeo

CNN Architectures (2/6)

Prueba de autoevaluación

CNN Architectures (3/6)

Vídeo

CNN Architectures (3/6)

Prueba de autoevaluación

CNN Architectures (4/6)

Vídeo

CNN Architectures (4/6)

Prueba de autoevaluación

CNN Architectures (5/6)

Vídeo

CNN Architectures (5/6)

Prueba de autoevaluación

CNN Architectures (6/6)

Vídeo

CNN Architectures (6/6)

Prueba de autoevaluación

Transformer

Vídeo

Transformer

Prueba de autoevaluación

Learning Material

Texto

Weekly Assignment

Prueba evaluada

Practical Exercise Week 2 - CIFAR 100

Practical Exercise Quiz

Prueba evaluada

Practical Exercise Week 2 - Solution

Texto

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

Texto

Neural Network Compression

Vídeo

Neural Network Compression

Prueba de autoevaluación

Compact Network Design (1/3)

Vídeo

Compact Network Design 1

Prueba de autoevaluación

Compact Network Design (2/3)

Vídeo

Compact Network Design 2

Prueba de autoevaluación

Compact Network Design (3/3)

Vídeo

Compact Network Design 3

Prueba de autoevaluación

Knowledge Distillation (1/2)

Vídeo

Knowledge Distillation 1

Prueba de autoevaluación

Knowledge Distillation (2/2)

Vídeo

Knowledge Distillation 2

Prueba de autoevaluación

Learning Material

Texto

Weekly Assignment

Prueba evaluada

Practical Exercise Week 3 - Knowledge Distillation

Practical Exercise Quiz

Prueba evaluada

Practical Exercise Week 3 - Solution

Texto

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

Texto

Network Pruning

Vídeo

Pruning

Prueba de autoevaluación

Dynamic Network

Vídeo

Dynamic Network

Prueba de autoevaluación

Supernet-Subnets Architecture Search

Vídeo

Supernet-subnets Architecture Search

Prueba de autoevaluación

Neural Network Quantization

Vídeo

Neural Network Quantization

Prueba de autoevaluación

Binary Neural Networks (1/2)

Vídeo

Binary Neural Networks 1

Prueba de autoevaluación

Binary Neural Networks (2/2)

Vídeo

Binary Neural Networks 2

Prueba de autoevaluación

Learning Material

Texto

Weekly Assignment

Prueba evaluada

Practical Exercise Week 4 - Binary Neural Networks

Practical Exercise Quiz

Prueba evaluada

Practical Exercise Week 4 - Solution

Texto

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

Texto

Introduction of Edge AI

Vídeo

Introduction of Edge AI

Prueba de autoevaluación

Training and Inference

Vídeo

Training and Inference

Prueba de autoevaluación

Federated Learning (1/3)

Vídeo

Federated Learning 1

Prueba de autoevaluación

Federated Learning (2/3)

Vídeo

Federated Learning 2

Prueba de autoevaluación

Federated Learning (3/3)

Vídeo

Federated Learning 3

Prueba de autoevaluación

Learning Material

Texto

Weekly Assignment

Prueba evaluada

Practical Exercise Week 5 - Federated Learning

Practical Exercise Quiz

Prueba evaluada

Practical Exercise Week 5 - Solution

Texto

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

Texto

Edge AI Computing Model

Vídeo

Edge AI Computing Model

Prueba de autoevaluación

Advanced ML Methods for Edge AI (1/2)

Vídeo

Advanced ML Methods for Edge AI 1

Prueba de autoevaluación

Advanced ML Methods for Edge AI (2/2)

Vídeo

Advanced ML Methods for Edge AI 2

Prueba de autoevaluación

Edge AI Hardware

Vídeo

Edge AI Hardware

Prueba de autoevaluación

Edge AI Application Scenarios

Vídeo

Application Scenarios

Prueba de autoevaluación

Learning Material

Texto

Weekly Assignment

Prueba evaluada

Practical Exercise Week 6 - Collaborative Inference

Practical Exercise Quiz

Prueba evaluada

Practical Exercise Week 6 - Solution

Texto

Week 7 - Final Exam

Final Exam

Final Exam

Texto

Final exam

Prueba evaluada

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?

Texto