Machine learning is one of the most sought-after skills in today’s data-driven world, and this course provides the perfect balance between theory and application. You’ll explore how Python can be leveraged to build, evaluate, and deploy machine learning models effectively across various domains.
Python Machine Learning By Example
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
For data scientists and ML engineers with Python knowledge; intermediate-level practical ML skills.
3 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
For data scientists and ML engineers with Python knowledge; intermediate-level practical ML skills.
3 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
Apply machine learning best practices in data preparation and model development
Build and refine image classifiers using convolutional neural networks and transfer learning
Develop and tune neural networks with TensorFlow and PyTorch
您将获得的技能
- Machine Learning
- Convolutional Neural Networks
- Model Optimization
- Predictive Modeling
- Model Training
- Image Analysis
- Data Preprocessing
- Applied Machine Learning
- Natural Language Processing
- Machine Learning Methods
- Transfer Learning
- Machine Learning Algorithms
- Reinforcement Learning
- Model Evaluation
- Deep Learning
- Large Language Modeling
- Computer Vision
要了解的详细信息
可分享的证书
添加到您的领英档案
最近已更新！
April 2026
作业
15 项作业
授课语言：英语（English）
91% of learners achieved a positive career outcome
了解顶级公司的员工如何掌握热门技能
该课程共有15个模块
In this section, we explore foundational machine learning concepts, data preprocessing, and model combination techniques using Python, emphasizing practical applications and model accuracy.
涵盖的内容
2个视频12篇阅读材料1个作业
2个视频•总计2分钟
- Course Overview•1分钟
- Getting Started with Machine Learning and Python - Overview Video•1分钟
12篇阅读材料•总计135分钟
- Introduction•10分钟
- Machine Learning Applications•10分钟
- A Brief History of the Development of Machine Learning Algorithms•10分钟
- Overfitting•10分钟
- The Bias-Variance Trade-Off•10分钟
- Avoiding Overfitting with Cross-Validation•10分钟
- Avoiding Overfitting with Regularization•10分钟
- Data Preprocessing and Feature Engineering•10分钟
- One-hot Encoding•10分钟
- Combining Models•15分钟
- Setting Up Python and Environments•20分钟
- TensorFlow•10分钟
1个作业•总计10分钟
- Introduction to Machine Learning Fundamentals•10分钟
In this section, we explore binary classification using Bayes to build a movie recommendation system, evaluate model performance, and apply cross-validation for refinement
涵盖的内容
1个视频7篇阅读材料1个作业
1个视频•总计1分钟
- Building a Movie Recommendation Engine with Naïve Bayes - Overview Video•1分钟
7篇阅读材料•总计115分钟
- Introduction•15分钟
- Exploring Naïve Bayes•15分钟
- The Mechanics of Naïve Bayes•20分钟
- Implementing Naïve Bayes from Scratch•20分钟
- Building a Movie Recommender with Naïve Bayes•15分钟
- Training a Naïve Bayes Model•20分钟
- Tuning Models with Cross-Validation•10分钟
1个作业•总计10分钟
- Movie Recommendation System Fundamentals•10分钟
In this section, we explore tree-based algorithms for predicting ad click-through rates, focusing on decision trees, random forests, and gradient-boosted trees with practical implementations using scikit-learn and XGBoost.
涵盖的内容
1个视频5篇阅读材料1个作业
1个视频•总计1分钟
- Predicting Online Ad Click-Through with Tree-Based Algorithms - Overview Video•1分钟
5篇阅读材料•总计100分钟
- Introduction•15分钟
- Gini Impurity•20分钟
- Implementing a Decision Tree from Scratch•20分钟
- Implementing a Decision Tree with Scikit-learn•25分钟
- Ensembling Decision Trees Random Forests•20分钟
1个作业•总计10分钟
- Tree-Based Algorithms in Ad Click Prediction•10分钟
In this section, we cover logistic regression, including encoding, training, regularization, and TensorFlow implementation for ad click prediction.
涵盖的内容
1个视频8篇阅读材料1个作业
1个视频•总计1分钟
- Predicting Online Ad Click-Through with Logistic Regression - Overview Video•1分钟
8篇阅读材料•总计135分钟
- Introduction•20分钟
- Jumping from the Logistic Function to Logistic Regression•20分钟
- Training a Logistic Regression Model Using Gradient Descent•20分钟
- Predicting Ad Click-Through with Logistic Regression Using Gradient Descent•15分钟
- Training a Logistic Regression Model with Regularization•20分钟
- Training on Large Datasets with Online Learning•10分钟
- Handling Multiclass Classification•15分钟
- Implementing Logistic Regression Using TensorFlow•15分钟
1个作业•总计10分钟
- Logistic Regression and Feature Engineering Fundamentals•10分钟
In this section, we explore regression techniques for stock price prediction, focusing on feature engineering, linear regression, and model evaluation for data-driven financial decisions.
涵盖的内容
1个视频7篇阅读材料1个作业
1个视频•总计1分钟
- Predicting Stock Prices with Regression Algorithms - Overview Video•1分钟
7篇阅读材料•总计120分钟
- Introduction•15分钟
- Getting Started with Feature Engineering•10分钟
- Acquiring Data and Generating Features•15分钟
- How Does Linear Regression Work?•20分钟
- Implementing Linear Regression with Scikit-learn•20分钟
- Implementing Decision Tree Regression•15分钟
- Implementing a Regression Forest•25分钟
1个作业•总计10分钟
- Regression Techniques in Financial Forecasting•10分钟
In this section, we cover building and optimizing neural networks for stock price prediction using activation functions, dropout, and early stopping.
涵盖的内容
1个视频6篇阅读材料1个作业
1个视频•总计1分钟
- Predicting Stock Prices with Artificial Neural Networks - Overview Video•1分钟
6篇阅读材料•总计115分钟
- Introduction•20分钟
- Backpropagation•15分钟
- Implementing Neural Networks from Scratch•20分钟
- Implementing Neural Networks with PyTorch•20分钟
- Early Stopping•20分钟
- Fine-tuning the Neural Network•20分钟
1个作业•总计10分钟
- Neural Networks in Financial Forecasting•10分钟
In this section, we explore text analysis techniques using NLP, focusing on preprocessing, visualizing newsgroups data with t-SNE, and applying unsupervised learning to unstructured data.
涵盖的内容
1个视频10篇阅读材料1个作业
1个视频•总计1分钟
- Mining the 20 Newsgroups Dataset with Text Analysis Techniques - Overview Video•1分钟
10篇阅读材料•总计135分钟
- Introduction•10分钟
- NLP Applications•15分钟
- Corpora•20分钟
- NER•10分钟
- Getting the Newsgroups Data•10分钟
- Exploring the Newsgroups Data•10分钟
- Counting the Occurrence of Each Word Token•15分钟
- Reducing Inflectional and Derivational Forms of Words•10分钟
- t-SNE for Dimensionality Reduction•15分钟
- Building Embedding Models Using Shallow Neural Networks•20分钟
1个作业•总计10分钟
- Exploring Text Analysis with the 20 Newsgroups Dataset•10分钟
In this section, we explore clustering and topic modeling to uncover hidden structures in text data. Techniques like k-means and NMF/LDA reveal underlying themes and groupings for practical data analysis.
涵盖的内容
1个视频7篇阅读材料1个作业
1个视频•总计1分钟
- Discovering Underlying Topics in the Newsgroups Dataset with Clustering and Topic Modeling - Overview Video•1分钟
7篇阅读材料•总计105分钟
- Introduction•10分钟
- Getting Started with K-Means Clustering•20分钟
- Implementing k-Means with scikit-learn•20分钟
- Clustering Newsgroups Data Using K-Means•15分钟
- Describing the Clusters Using GPT•10分钟
- Discovering Underlying Topics in Newsgroups•10分钟
- Topic Modeling Using LDA•20分钟
1个作业•总计10分钟
- Exploring Text Data Analysis Techniques•10分钟
In this section, we explore SVM for face recognition, analyze hyperplane separation in high-dimensional data, and apply PCA to enhance image classification performance.
涵盖的内容
1个视频5篇阅读材料1个作业
1个视频•总计1分钟
- Recognizing Faces with Support Vector Machine - Overview Video•1分钟
5篇阅读材料•总计105分钟
- Introduction•20分钟
- Handling Outliers•20分钟
- Multiclass Cases in Scikit-learn•25分钟
- Choosing Between Linear and RBF Kernels•20分钟
- Building an SVM-Based Image Classifier•20分钟
1个作业•总计10分钟
- Exploring SVM Techniques and Applications•10分钟
In this section, we explore 21 machine learning best practices, focusing on data preparation, model selection, and continuous monitoring to ensure effective real-world implementations.
涵盖的内容
1个视频8篇阅读材料1个作业
1个视频•总计1分钟
- Machine Learning Best Practices - Overview Video•1分钟
8篇阅读材料•总计120分钟
- Introduction•10分钟
- Best Practice 4 Dealing with Missing Data•20分钟
- Best practice 5 – Storing large-scale data•10分钟
- Best Practice 10 Deciding Whether to Rescale Features•15分钟
- TF and TF-IDF•15分钟
- Best practices in the model training, evaluation, and selection stage•15分钟
- Best Practice Reducing Overfitting•15分钟
- Saving and Restoring Models Using Pickle•20分钟
1个作业•总计10分钟
- Machine Learning Data Preparation Essentials•10分钟
In this section, we explore CNNs for clothing image classification, focusing on building blocks, model design, and data augmentation techniques to enhance performance.
涵盖的内容
1个视频5篇阅读材料1个作业
1个视频•总计1分钟
- Categorizing Images of Clothing with Convolutional Neural Networks - Overview Video•1分钟
5篇阅读材料•总计105分钟
- Introduction•10分钟
- The Pooling Layer•25分钟
- Classifying Clothing Images with CNNs•20分钟
- Fitting the CNN Model•25分钟
- Rotation for Data Augmentation•25分钟
1个作业•总计10分钟
- Exploring Convolutional Neural Networks for Clothing Image Classification•10分钟
In this section, we explore RNNs and LSTMs for sequence prediction, focusing on training models to handle time-dependent data and generate text with practical applications.
涵盖的内容
1个视频7篇阅读材料1个作业
1个视频•总计1分钟
- Making Predictions with Sequences Using Recurrent Neural Networks - Overview Video•1分钟
7篇阅读材料•总计110分钟
- Introduction•15分钟
- One-to-many RNNs•20分钟
- Analyzing and Preprocessing the Data•20分钟
- Building a Simple LSTM Network•15分钟
- Revisiting Stock Price Forecasting with LSTM•10分钟
- Writing Your Own War and Peace with RNNs•20分钟
- Building and Training an RNN Text Generator•10分钟
1个作业•总计10分钟
- Exploring Sequence Modeling with RNNs•10分钟
In this section, we explore Transformer models, focusing on self-attention mechanisms and their application in NLP tasks like sentiment analysis and text generation using BERT and GPT.
涵盖的内容
1个视频7篇阅读材料1个作业
1个视频•总计1分钟
- Advancing Language Understanding and Generation with the Transformer Models - Overview Video•1分钟
7篇阅读材料•总计120分钟
- Introduction•10分钟
- Attention Score Calculation and Embedding Vector Generation•25分钟
- Multi-head Attention•10分钟
- Positional Encoding•20分钟
- Fine-tuning a Pre-trained BERT Model for Sentiment Analysis•20分钟
- Using the Trainer API to Train Transformer Models•15分钟
- Writing Your Own Version of War and Peace with GPT•20分钟
1个作业•总计10分钟
- Exploring Transformer Architecture and Applications•10分钟
In this section, we cover CLIP for image and text retrieval, focusing on contrastive learning and zero-shot classification.
涵盖的内容
1个视频7篇阅读材料1个作业
1个视频•总计1分钟
- Building an Image Search Engine Using CLIP a Multimodal Approach - Overview Video•1分钟
7篇阅读材料•总计110分钟
- Introduction•15分钟
- Zero-shot Image Classification•10分钟
- Getting Started with the Dataset•20分钟
- Vision Encoder•15分钟
- CLIP Model•10分钟
- Obtaining Embeddings for Images and Text to Identify Matches•25分钟
- Zero-shot Classification•15分钟
1个作业•总计10分钟
- Multimodal Models in Image Search•10分钟
In this section, we cover decision-making in complex environments using reinforcement learning.
涵盖的内容
1个视频8篇阅读材料1个作业
1个视频•总计1分钟
- Making Decisions in Complex Environments with Reinforcement Learning - Overview Video•1分钟
8篇阅读材料•总计150分钟
- Introduction•20分钟
- Cumulative Rewards•10分钟
- Simulating the FrozenLake Environment•25分钟
- Solving FrozenLake with the Value Iteration Algorithm•20分钟
- Solving FrozenLake with the Policy Iteration Algorithm•20分钟
- Simulating the Blackjack Environment•20分钟
- Performing On-Policy Monte Carlo Control•15分钟
- Introducing the Q-Learning Algorithm•20分钟
1个作业•总计10分钟
- Reinforcement Learning Fundamentals•10分钟
位教师
提供方
提供方
Packt
Packt helps tech professionals put software to work by distilling and sharing the working knowledge of their peers. Packt is an established global technical learning content provider, founded in Birmingham, UK, with over twenty years of experience delivering premium, rich content from groundbreaking authors on a wide range of emerging and popular technologies.
从 Machine Learning 浏览更多内容
课程
AArizona State University
课程
OO.P. Jindal Global University
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
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 purchase a Certificate you get access to all course materials, including graded assignments. Upon completing the course, 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，