Fundamentals of Deep Learning

位教师：Whizlabs Instructor

访问权限由 Coursera Learning Team 提供

2个模块

深入了解一个主题并学习基础知识。

中级等级

推荐体验

6 小时完成

灵活的计划

自行安排学习进度

2个模块

深入了解一个主题并学习基础知识。

中级等级

推荐体验

6 小时完成

灵活的计划

自行安排学习进度

您将获得的技能

要了解的详细信息

可分享的证书

添加到您的领英档案

作业

4 项作业

授课语言：英语（English）

了解顶级公司的员工如何掌握热门技能

了解关于 Coursera for Business 的更多信息

Petrobras, TATA, Danone, Capgemini, P&G 和 L'Oreal 的徽标

该课程共有2个模块

Fundamentals of Deep Learning is a structured course designed for developers, data professionals, and AI enthusiasts who want to build a strong foundation in neural networks and modern deep learning techniques. This course focuses on core deep learning principles, including how artificial neurons work, forward and backward propagation, gradient descent optimization, activation functions, multi-class classification, Convolutional Neural Networks (CNNs), and transfer learning.

Through a progressive and practical learning path, you will gain hands-on experience training neural networks, evaluating model performance, and applying deep learning techniques to real-world image classification problems. The course bridges theory and implementation, helping you understand not just how models work, but why they work. Whether you are beginning your journey in artificial intelligence or preparing for advanced machine learning and cloud-based AI roles, this course equips you with the conceptual clarity and practical skills required to confidently build and evaluate deep learning models. This course includes approximately 3:30–4:00 hours of video lectures, combining foundational theory with step-by-step demonstrations. It is divided into focused modules that progressively develop your understanding of neural network architecture and applied deep learning techniques. To reinforce learning, each module includes quizzes and in-video practice questions that test conceptual understanding and practical application. 📘 Module 1: Foundations of Deep Learning and Neural Networks 🧠 Module 2: Deep Learning Models, Computer Vision, and Transfer Learning

Welcome to Week 1 of the Fundamentals of Deep Learning course. In this week, you will be introduced to the core concepts of deep learning and set clear expectations for what you will learn throughout the course. We will begin by understanding what deep learning is and how it fits within the broader fields of artificial intelligence and machine learning. You will explore how data is processed inside a neuron, gaining insight into the building blocks of neural networks. The week then focuses on how deep learning models learn, covering key concepts such as gradient descent, forward propagation, and backward propagation. Through demonstrations, you will see how a neuron is trained and how activation functions enable neural networks to learn complex, non-linear patterns. By the end of this week, you will have a strong foundational understanding of deep learning fundamentals, including how neural networks are structured, how learning and optimization take place, and the role of activation functions in training deep learning models.

涵盖的内容

9个视频2篇阅读材料2个作业

9个视频总计53分钟

What is Deep Learning?6分钟
Expectations from Fundamentals of Deep Learning1分钟
How Data is Processed in a Neuron6分钟
Gradient Descent9分钟
Training a Neuron – Demo8分钟
Deep Learning Neural Network – Forward Propagation4分钟
Backward Propagation – Deep Learning Neural Network5分钟
Activation Functions6分钟
Activation Functions – Demo9分钟

2篇阅读材料总计60分钟

Welcome to the Course30分钟
Overview of Foundations of Deep Learning and Neural Networks30分钟

2个作业总计75分钟

Core Concepts and Learning Mechanics of Deep Learning - Knowledge Check40分钟
Foundations of Deep Learning and Neural Networks - Assessment35分钟

Welcome to Week 2 of the Fundamentals of Deep Learning course. This week focuses on the practical application of deep learning techniques for real-world problems, with an emphasis on model training, evaluation, and modern neural network architectures. You will begin by working on multi-class classification using the MNIST dataset, where you will train and evaluate a deep learning model and understand how performance is measured. The week then introduces Convolutional Neural Networks (CNNs), explaining how they are designed to effectively learn from image data. You will also explore transfer learning techniques, learning how pre-trained models can be reused and adapted for new tasks. Through hands-on demonstrations, you will implement transfer learning on an image dataset and evaluate model performance. By the end of this week, you will be able to train and evaluate deep learning models for classification tasks, understand CNN-based architectures, and apply transfer learning to efficiently solve image-based deep learning problems.

涵盖的内容

5个视频2篇阅读材料2个作业

5个视频总计43分钟

Multi-Class Classification with MNIST Dataset – Deep Learning14分钟
Training Multiclass Classifier – Fit and Evaluate7分钟
Understanding Convolutional Neural Networks (CNNs)9分钟
Transfer Learning Techniques6分钟
Implementing Transfer Learning on an Image Dataset – Demo6分钟

2篇阅读材料总计40分钟

Overview of Deep Learning Models, Computer Vision, and Transfer Learning30分钟
What's Next ?10分钟

2个作业总计60分钟

Applied Deep Learning: CNNs, Classification, and Transfer Learning - Knowledge Check30分钟
Deep Learning Models, Computer Vision, and Transfer Learning - Assessment30分钟