Gain hands-on experience in deep learning with Python and learn to design, train, and optimize advanced neural networks for real-world artificial intelligence applications. This course is ideal for data scientists, machine learning engineers, and AI enthusiasts who want to enhance their skills in building intelligent systems using Python.
Practical Deep Learning with Python
深入了解一个主题并学习基础知识。
中级 等级
推荐体验
推荐体验
中级
Experience in building machine learning models, Statistics and Python as a programming language is recommended.
1 周 完成
在 10 小时 一周
灵活的计划
自行安排学习进度
深入了解一个主题并学习基础知识。
中级 等级
推荐体验
推荐体验
中级
Experience in building machine learning models, Statistics and Python as a programming language is recommended.
1 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
Understand the core components of deep learning models and their role in AI.
Apply CNN, R-CNN, and Faster R-CNN for object detection tasks.
Implement RNNs and LSTMs for sequential data processing.
Optimize and evaluate deep learning models for improved performance.
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
作业
13 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
积累特定领域的专业知识
本课程是 Mastering AI: Neural Nets, Vision System, Speech Recognition 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4个模块
In this module, you will explore the fundamental components of deep learning by designing perceptron and implementing their functionality. You will address the limitations of perceptron by utilizing Multi-Layer Perceptron (MLPs) and observe how MLPs significantly enhance model performance.
涵盖的内容
25个视频4篇阅读材料4个作业2个讨论话题
25个视频• 总计113分钟
- Course Introduction• 5分钟
- Environment Configuration• 2分钟
- Machine Learning vs. Deep Learning• 5分钟
- What is Deep Learning?• 3分钟
- Neural Networks• 6分钟
- Artificial Neural Network (ANN)• 6分钟
- ANN: Types and Applications• 4分钟
- Forward Propagation• 4分钟
- Perceptron• 7分钟
- Learning Rate• 7分钟
- What is Activation Function? • 4分钟
- Activation Function and it's Types• 5分钟
- Importance of Epoch• 5分钟
- Single Layer Perceptron - Define Sigmoid Function • 6分钟
- Single Layer Perceptron - Decision Boundary• 7分钟
- Limitations of Single Layered Perceptron• 2分钟
- Multi-Layered Perceptron• 2分钟
- What is Backpropagation? • 2分钟
- Backpropagation • 3分钟
- Demonstration: Building a Simple Neural Network• 4分钟
- Demonstration: Understanding How Backpropagation has Worked• 4分钟
- Demonstration: Handwritten Digits Classification - Data Preprocessing • 4分钟
- Demonstration: Handwritten Digits Classification- Designing the Model• 5分钟
- Demonstration: Handwritten Digits Classification - Optimizing the Model • 5分钟
- Summary of Deep Learning Components• 6分钟
4篇阅读材料• 总计40分钟
- Welcome to Practical Deep Learning with Python• 10分钟
- System Requirements and Pre-requisite for Studying Deep Learning• 10分钟
- Learning Rate in Deep Learning• 10分钟
- Hebbian Learning Algorithm• 10分钟
4个作业• 总计48分钟
- Knowledge Check : Deep Learning Components• 30分钟
- Practice Quiz : Environment Set-Up and Configuration• 6分钟
- Practice Quiz : Essentials for Deep Learning• 6分钟
- Practice Quiz : Building Perceptron and it's Working• 6分钟
2个讨论话题• 总计20分钟
- Introduce Yourself• 10分钟
- What are the structural and functional similarities between the human brain and neural networks?• 10分钟
In the second module of this course, learners will learn about the working of Convolutional Neural Networks (CNN) and understand their importance in training deep learning models. Learners will also work on improving CNN model performance using RCNN and Faster RCNN, observe the computation time of these models, and gauge their accuracy score.
涵盖的内容
27个视频3篇阅读材料4个作业1个讨论话题
27个视频• 总计126分钟
- Limitations of MLP• 4分钟
- MLP Limitations: Resolving the Issue with CNN• 3分钟
- Visual Cortex and CNN• 7分钟
- Convolutional Layer • 6分钟
- Working of Convolutional Layer • 6分钟
- Demonstration: Load and Preprocess the Data • 5分钟
- Demonstration: Designing the Model • 5分钟
- Demonstration: Building the CNN Model • 3分钟
- Demonstration: Model Accuracy • 2分钟
- Demonstration: Adding More Layers • 5分钟
- Demonstration: Building Basic CNN Model with New Parameters• 5分钟
- Demonstration: Pre-trained Model • 3分钟
- Classification and Object Detection• 6分钟
- Introduction to RCNN• 5分钟
- R-CNN: Bounding Box Regression• 2分钟
- Pre-trained Model• 6分钟
- Fast Regional - CNN• 6分钟
- Demonstration: Creating Base Variables and Loading the Model• 4分钟
- Demonstration: Training the Model and Visualizing the Predictions• 4分钟
- Demonstration: SVM as a Classifier• 3分钟
- Fast RCNN Limitations• 5分钟
- Advent of Faster R-CNN• 6分钟
- Tensorflow Hub• 4分钟
- Demonstration: Object Detection with Faster RCNN-Pretrained Model setup• 6分钟
- Demonstration: Object Detection with Faster RCNN - Building the Model• 6分钟
- Summary of CNN in Deep Learning• 3分钟
- Summary of Faster RCNN• 4分钟
3篇阅读材料• 总计30分钟
- Why Convolutions are Important?• 10分钟
- SVM Classifier in Object Detection • 10分钟
- Faster R-CNN Architecture• 10分钟
4个作业• 总计48分钟
- Knowledge Check : Deep Learning with CNN, RCNN and Faster RCNN• 30分钟
- Practice Quiz : CNN• 6分钟
- Practice Quiz : TensorFlow Hub for Object Detection using Faster RCNN• 6分钟
- Practice Quiz : Faster RCNN (Recurrent Convolutional Neural Network)• 6分钟
1个讨论话题• 总计10分钟
- Which among the following techniques is most useful?• 10分钟
This module focuses on Recurrent Neural Networks (RNNs) and Long Short-Term Memory (LSTM) networks for sequential data processing. Learners will gain practical skills in building, training, and optimizing models for complex tasks.
涵盖的内容
24个视频4篇阅读材料4个作业
24个视频• 总计126分钟
- RNN Fundamentals• 5分钟
- RNN Architecture• 4分钟
- RNN Architecture: Workflow• 5分钟
- Implementing RNN• 7分钟
- Demonstration: RNN-Dataset Preparation • 6分钟
- Demonstration: RNN-Building the Model • 6分钟
- Basics of LSTM• 6分钟
- LSTM Structure• 6分钟
- Forget Gate and Input Gate• 6分钟
- Output Gate• 3分钟
- Importance of LSTM Architecture• 5分钟
- Types of LSTM• 4分钟
- Demonstration: Next Word Prediction- Processing the Corpus• 6分钟
- Demonstration: Next Word Prediction- Layers • 5分钟
- Demonstration: Next Word Prediction- Model Compilation and Prediction• 7分钟
- Improving a Model• 6分钟
- Model Optimization• 4分钟
- Using Adam Optimizer• 7分钟
- Model Compilation• 3分钟
- Model Compilation with Popular Frameworks• 4分钟
- Demonstration: Model Compilation- Preparing the Dataset• 5分钟
- Demonstration: Building and Compiling Model • 5分钟
- Demonstration: From RMSProp to Adam • 4分钟
- Summary of Deep Learning with RNN and LSTM with Model Optimization• 5分钟
4篇阅读材料• 总计40分钟
- Recurrent Neural Networks (RNNs) in Deep Learning• 10分钟
- Attention-Based LSTM (Long Short-Term Memory)• 10分钟
- Capsule Networks in Deep Learning• 10分钟
- Model Optimizers: Beyond ADAM• 10分钟
4个作业• 总计48分钟
- Knowledge Check : Deep Learning with RNN, LSTM and Model Optimization• 30分钟
- Practice Quiz : Working of Recurrent Neural Networks (RNN)• 6分钟
- Practice Quiz : LSTM Architecture and Working• 6分钟
- Practice Quiz : Module Optimization and Compilation• 6分钟
This module is designed to assess an individual on the various concepts and teachings covered in this course. Evaluate your knowledge with a comprehensive graded quiz on SLP, MLP, RNN, CNN, LSTM and many more complex deep learning concepts.
涵盖的内容
1个视频1篇阅读材料1个作业1个讨论话题
1个视频• 总计4分钟
- Course Summary for Practical Deep Learning with Python• 4分钟
1篇阅读材料• 总计10分钟
- Practice Project: MNIST Fashion Dataset - Analysis• 10分钟
1个作业• 总计30分钟
- Knowledge Check : Practical Deep Learning with Python• 30分钟
1个讨论话题• 总计10分钟
- Describe Your Learning Journey• 10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
提供方
提供方
Edureka
Edureka is an online education platform focused on delivering high-quality learning to working professionals. We have the highest course completion rate in the industry and we strive to create an online ecosystem for our global learners to equip themselves with industry-relevant skills in today’s cutting edge technologies.
从 Machine Learning 浏览更多内容
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。'
常见问题
Deep learning is a subset of machine learning that emphasizes artificial neural network algorithms designed to mimic the structure and functions of the human brain. Multi-layered neural networks are developed to autonomously learn and identify features from vast datasets, enabling them to effectively perform tasks such as speech recognition, image recognition, and natural language processing. Deep learning plays a crucial role in AI advancements as it requires extensive amounts of data and computational strength.
The target audience for Practical Deep Learning with Python comprises beginners and intermediate learners eager to grasp and utilize deep learning methods with Python. This course is tailored for for data scientists, AI Research Analysts, and developers who possess fundamental programming skills and a basic grasp of machine learning principles.
To effectively follow the exercises and examples in Practical Deep Learning with Python, you will need a computer with the following minimum system requirements:
- Operating System: Windows, macOS, or Linux.
- Processor: A multi-core processor (preferably with support for AVX instructions).
- RAM: At least 8 GB of RAM, though 16 GB or more is recommended for larger datasets.
- Storage: At least 10 GB of free disk space to accommodate datasets, libraries, and project files.
- Python Environment: Python 3.6 or later installed with libraries such as TensorFlow or PyTorch, NumPy, Matplotlib, and Pandas.
Please note: All the practical are performed on Google Colab
To effectively learn deep learning, it is advisable to acquire the following essential knowledge and skills:
- Mathematics: A solid grasp of linear algebra (matrices, vectors), calculus (derivatives and gradients), probability, and fundamental statistics. These ideas are essential for grasping the workings of neural networks and the process of optimization.
- Programming Abilities: Mastery of Python is crucial, since the majority of deep learning frameworks, such as TensorFlow and PyTorch, are built on Python. Having knowledge of libraries like NumPy, Pandas, and Matplotlib is also advantageous.
- Machine Learning Essentials: Grasping the core principles of machine learning, including supervised and unsupervised learning, overfitting, underfitting, and evaluation metrics for models, will establish a solid groundwork.
Data Management: Familiarity with data preprocessing methods, such as addressing missing data, normalization, and data augmentation, is beneficial.
The course uses Python along with TensorFlow, Keras, and supporting libraries like NumPy and Pandas.
Yes, you’ll learn perceptrons, multilayer perceptrons, convolutional neural networks, and more.
Absolutely. Deep learning is a core skill for data science, AI engineering, and research roles across industries.
This course focuses specifically on deep neural networks, feature learning, and large-scale AI applications.
Yes, you’ll receive a Coursera certificate to showcase your deep learning expertise to employers and on LinkedIn.
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.
更多问题
提供助学金，