Introduction to Deep Learning

Introduction to Deep Learning

本课程是 Machine Learning: Theory and Hands-on Practice with Python 专项课程的一部分

位教师：Daniel E. Acuna

包含在中

了解更多

5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

2 周完成

在 10 小时一周

灵活的计划

自行安排学习进度

5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

2 周完成

在 10 小时一周

灵活的计划

自行安排学习进度

您将学到什么

Explain the mathematical foundations of neural networks and how they learn from data.
Train and regularize deep neural networks for effective generalization.
Design and apply specialized neural network architectures for images and sequences.
Apply transformer-based and multimodal models to real-world scenarios.

您将获得的技能

您将学习的工具

要了解的详细信息

可分享的证书

添加到您的领英档案

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

积累特定领域的专业知识

本课程是 Machine Learning: Theory and Hands-on Practice with Python 专项课程专项课程的一部分

在注册此课程时，您还会同时注册此专项课程。

向行业专家学习新概念
获得对主题或工具的基础理解
通过实践项目培养工作相关技能
获得可共享的职业证书

该课程共有5个模块

Introduction to Deep Learning provides a rigorous, concept-driven introduction to the models that power modern AI systems—from image recognition to large language models. You’ll build neural networks from first principles, understanding how forward passes, loss functions, and backpropagation enable learning. As the course progresses, you’ll train and regularize deep models, design convolutional networks for vision, model sequences with RNNs, LSTMs, and attention, and apply transformer-based architectures such as BERT, GPT, and Vision Transformers. You will also look at the latest trends in contrastive learning and CLIP. By combining mathematical foundations with practical application, this course equips you to understand, train, and use deep learning models with confidence.

This course can be taken for academic credit as part of CU Boulder’s Masters of Science in Computer Science (MS-CS), Master of Science in Artificial Intelligence (MS-AI), and Master of Science in Data Science (MS-DS) degrees offered on the Coursera platform. These fully accredited graduate degrees offer targeted courses, short 8-week sessions, and pay-as-you-go tuition. Admission is based on performance in three preliminary courses, not academic history. CU degrees on Coursera are ideal for recent graduates or working professionals. Learn more: MS in Artificial Intelligence: https://hua.dididi.sbs/degrees/ms-artificial-intelligence-boulder MS in Computer Science: https://coursera.org/degrees/ms-computer-science-boulder MS in Data Science: https://hua.dididi.sbs/degrees/master-of-science-data-science-boulder

Welcome to Introduction to Deep Learning. This module builds the mathematical foundations of neural networks. Starting from linear models, you will learn about the artificial neuron and develop the mathematics of gradient descent and backpropagation. The focus is on understanding how and why neural networks work through the underlying math—covering the forward pass, loss functions, and the chain rule to show how information flows through networks and how they learn from data.

涵盖的内容

15个视频6篇阅读材料2个作业1个编程作业

15个视频总计104分钟

Machine Learning Introduction 2分钟
Deep Learning Introduction 2分钟
Academic Integrity and AI Use Policy for the Machine Learning Specialization 9分钟
From Linear Regression to the Artificial Neuron 9分钟
Activation Functions and Non-Linearity: The Mathematical Notation and Problem Setup 5分钟
Activation Functions and Non-Linearity: Why Non-Linearity is Important 6分钟
Activation Functions and Non-Linearity: Sigmoid Activation and its Gradient 10分钟
Activation Functions and Non-Linearity: Rectified Linear Unit Activation and its Gradient 4分钟
Activation Functions and Non-Linearity: Other Activations and How to Choose Among Them 4分钟
Layers, Depth, and Forward Propagation 10分钟
Matrix Notation and Dimensions 9分钟
Loss Functions: MSE and Cross-Entropy 7分钟
Gradient Descent: The Math of Optimization 8分钟
The Chain Rule and Backpropagation 9分钟
Backpropagation Through a Network 10分钟

6篇阅读材料总计96分钟

Course Updates and Accessibility Support 1分钟
Earn Academic Credit for Your Work! 10分钟
Course Support 10分钟
Assessment Expectations 5分钟
Download the Recommended Reading for This Course 10分钟
From Linear Models to Neural Networks - Recommended Reading 60分钟

2个作业总计35分钟

AI Policy Quiz 5分钟
Neural Network Foundations 30分钟

1个编程作业总计60分钟

Lab 1: Building and Training Your First Neural Network in Keras 60分钟

This module focuses on training neural networks effectively. Topics include optimization algorithms, hyperparameter tuning, and regularization techniques to prevent overfitting and achieve good generalization. You will compare different optimizers like SGD, momentum, and Adam, understand how learning rate and batch size affect training dynamics, and apply weight decay, dropout, early stopping, and batch normalization.

涵盖的内容

7个视频2篇阅读材料1个作业1个编程作业

7个视频总计43分钟

SGD, Momentum, and Adam 8分钟
Learning Rate and Batch Size 7分钟
Epochs and Monitoring Training 6分钟
Understanding Overfitting 6分钟
L2 Regularization (Weight Decay) 6分钟
Dropout 5分钟
Early Stopping and Batch Normalization 7分钟

2篇阅读材料总计90分钟

Optimization Algorithms - Recommended Reading 60分钟
Regularization Techniques - Recommended Reading 30分钟

1个作业总计30分钟

Training and Regularizing Neural Networks 30分钟

1个编程作业总计60分钟

Lab 2: Applying Regularization to Improve Model Generalization 60分钟

This module introduces you to convolutional neural networks (CNNs), the foundation of modern computer vision. Topics include how convolutional and pooling layers work, CNN architecture design, and practical techniques like data augmentation and transfer learning. The module covers classic architectures like VGG and ResNet and explains why CNNs outperform fully-connected networks on image data.

涵盖的内容

7个视频2篇阅读材料1个作业1个编程作业

7个视频总计51分钟

Why CNNs for Images? 8分钟
The Convolution Operation 8分钟
Pooling Layers 5分钟
CNN Architecture: Conv → Pool → Dense 7分钟
VGG, ResNet, and Skip Connections 9分钟
Data Augmentation 6分钟
Transfer Learning 7分钟

2篇阅读材料总计75分钟

Introduction to CNNs - Recommended Reading 45分钟
Training CNNs in Practice - Recommended Reading 30分钟

1个作业总计30分钟

Convolutional Neural Networks for Image Recognition 30分钟

1个编程作业总计60分钟

Lab 3: Training a CNN for Image Classification with Augmentation 60分钟

This module covers sequence modeling, starting with recurrent neural networks (RNNs) and long short-term memory networks (LSTMs), then progressing to the attention mechanism—the key innovation that led to transformers. Topics include how RNNs maintain hidden states across time steps, why the vanishing gradient problem motivated LSTMs, and how attention allows models to focus on relevant parts of their input.

涵盖的内容

7个视频1篇阅读材料1个作业1个编程作业

7个视频总计48分钟

Sequential Data and RNN Architecture 7分钟
Hidden State and Backprop Through Time 7分钟
LSTM Architecture 7分钟
The Attention Mechanism 8分钟
Self-Attention and QKV 8分钟
Multi-Head Attention 4分钟
Positional Encoding 6分钟

1篇阅读材料总计60分钟

Recurrent Neural Networks - Recommended Reading 60分钟

1个作业总计30分钟

Sequence Modeling – RNNs, LSTMs, and the Attention Mechanism 30分钟

1个编程作业总计60分钟

Lab 4: Building a Sequence Model with Attention 60分钟

This final module covers the transformer architecture, which has revolutionized deep learning across domains. Topics include BERT and GPT as encoder-only and decoder-only variants, Vision Transformers (ViT) that apply attention to images, and CLIP for multimodal learning connecting vision and language. The module emphasizes applying pre-trained models to real tasks.

涵盖的内容

8个视频1篇阅读材料1个作业1个编程作业

8个视频总计50分钟

The Transformer Architecture 6分钟
Encoder and Decoder Structure 7分钟
Layer Normalization in Transformers 6分钟
BERT: Encoder-Only Transformer 5分钟
GPT: Decoder-Only Transformer 5分钟
Vision Transformer (ViT) 7分钟
CLIP and Contrastive Learning 5分钟
Zero-Shot Classification with CLIP 9分钟

1篇阅读材料总计30分钟

The Transformer Architecture - Recommended Reading 30分钟

1个作业总计30分钟

Transformers, Vision Transformers, and CLIP 30分钟

1个编程作业总计60分钟

Lab 5: Using Pre-trained Vision Transformers and CLIP for Image Classification 60分钟

获得职业证书

将此证书添加到您的 LinkedIn 个人资料、简历或履历中。在社交媒体和绩效考核中分享。

位教师

Daniel E. Acuna

University of Colorado Boulder

3 门课程 3,098 名学生

提供方

University of Colorado Boulder

从 Machine Learning 浏览更多内容

Pearson
Learning Deep Learning: Unit 1
课程
MathWorks
Introduction to Deep Learning for Computer Vision
课程
IBM
Introduction to Deep Learning & Neural Networks with Keras
课程
University of Colorado Boulder
Deep Learning for Computer Vision
课程

人们为什么选择 Coursera 来帮助自己实现职业发展

Felipe M.

自 2018开始学习的学生

''能够按照自己的速度和节奏学习课程是一次很棒的经历。只要符合自己的时间表和心情，我就可以学习。'

Jennifer J.

自 2020开始学习的学生

''我直接将从课程中学到的概念和技能应用到一个令人兴奋的新工作项目中。'

Larry W.

自 2021开始学习的学生

''如果我的大学不提供我需要的主题课程，Coursera 便是最好的去处之一。'

Chaitanya A.

''学习不仅仅是在工作中做的更好：它远不止于此。Coursera 让我无限制地学习。'

通过 Coursera Plus 开启新生涯

无限制访问 10,000+ 世界一流的课程、实践项目和就业就绪证书课程 - 所有这些都包含在您的订阅中

了解更多

通过在线学位推动您的职业生涯

获取世界一流大学的学位 - 100% 在线

探索学位

加入超过 3400 家选择 Coursera for Business 的全球公司

提升员工的技能，使其在数字经济中脱颖而出

了解更多

常见问题

To access the course materials, assignments and to earn a Certificate, you will need to purchase the Certificate experience when you enroll in a course. You can try a Free Trial instead, or apply for Financial Aid. The course may offer 'Full Course, No Certificate' instead. This option lets you see all course materials, submit required assessments, and get a final grade. This also means that you will not be able to purchase a Certificate experience.

When you enroll in the course, you get access to all of the courses in the Specialization, and you earn a certificate when you complete the work. Your electronic Certificate will be added to your Accomplishments page - from there, you can print your Certificate or add it to your LinkedIn profile.

Yes. In select learning programs, you can apply for financial aid or a scholarship if you can’t afford the enrollment fee. If fin aid or scholarship is available for your learning program selection, you’ll find a link to apply on the description page.