Python Machine Learning By Example
Keep adding new skills with 10,000+ programs for $239 (usually $399). Save now.
Python Machine Learning By Example
Included with
Ask Coursera
Recommended experience
Recommended experience
What you'll learn
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
Skills you'll gain
- Large Language Modeling
- Natural Language Processing
- Computer Vision
- Artificial Intelligence and Machine Learning (AI/ML)
- Transfer Learning
- Machine Learning Methods
- Machine Learning Algorithms
- Model Optimization
- Machine Learning
- Convolutional Neural Networks
- Model Evaluation
- Model Training
- Deep Learning
- Applied Machine Learning
- Data Preprocessing
- Image Analysis
- Reinforcement Learning
Tools you'll learn
Details to know
April 2026
15 assignments
See how employees at top companies are mastering in-demand skills
There are 15 modules in this course
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.
Through this course, you’ll gain hands-on experience with practical tools and techniques to improve your ability to design, train, and optimize predictive models. You’ll learn how to apply advanced methods in areas such as deep learning, computer vision, and natural language processing to achieve measurable, real-world outcomes. What sets this course apart is its focus on bridging theoretical foundations with practical, implementation-based exercises. You’ll work on real-world case studies using TensorFlow and PyTorch, ensuring that the skills you acquire are immediately applicable in professional settings. This course is ideal for data scientists, ML engineers, and Python developers aiming to strengthen their expertise in applied machine learning. A working knowledge of Python and basic data analysis concepts will help you get the most out of this course.
In this section, we explore foundational machine learning concepts, data preprocessing, and model combination techniques using Python, emphasizing practical applications and model accuracy.
What's included
2 videos12 readings1 assignment
2 videos•Total 2 minutes
- Course Overview•1 minute
- Getting Started with Machine Learning and Python - Overview Video•1 minute
12 readings•Total 135 minutes
- Introduction•10 minutes
- Machine Learning Applications•10 minutes
- A Brief History of the Development of Machine Learning Algorithms•10 minutes
- Overfitting•10 minutes
- The Bias-Variance Trade-Off•10 minutes
- Avoiding Overfitting with Cross-Validation•10 minutes
- Avoiding Overfitting with Regularization•10 minutes
- Data Preprocessing and Feature Engineering•10 minutes
- One-hot Encoding•10 minutes
- Combining Models•15 minutes
- Setting Up Python and Environments•20 minutes
- TensorFlow•10 minutes
1 assignment•Total 10 minutes
- Introduction to Machine Learning Fundamentals•10 minutes
In this section, we explore binary classification using Bayes to build a movie recommendation system, evaluate model performance, and apply cross-validation for refinement
What's included
1 video7 readings1 assignment
1 video•Total 1 minute
- Building a Movie Recommendation Engine with Naïve Bayes - Overview Video•1 minute
7 readings•Total 115 minutes
- Introduction•15 minutes
- Exploring Naïve Bayes•15 minutes
- The Mechanics of Naïve Bayes•20 minutes
- Implementing Naïve Bayes from Scratch•20 minutes
- Building a Movie Recommender with Naïve Bayes•15 minutes
- Training a Naïve Bayes Model•20 minutes
- Tuning Models with Cross-Validation•10 minutes
1 assignment•Total 10 minutes
- Movie Recommendation System Fundamentals•10 minutes
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.
What's included
1 video5 readings1 assignment
1 video•Total 1 minute
- Predicting Online Ad Click-Through with Tree-Based Algorithms - Overview Video•1 minute
5 readings•Total 100 minutes
- Introduction•15 minutes
- Gini Impurity•20 minutes
- Implementing a Decision Tree from Scratch•20 minutes
- Implementing a Decision Tree with Scikit-learn•25 minutes
- Ensembling Decision Trees Random Forests•20 minutes
1 assignment•Total 10 minutes
- Tree-Based Algorithms in Ad Click Prediction•10 minutes
In this section, we cover logistic regression, including encoding, training, regularization, and TensorFlow implementation for ad click prediction.
What's included
1 video8 readings1 assignment
1 video•Total 1 minute
- Predicting Online Ad Click-Through with Logistic Regression - Overview Video•1 minute
8 readings•Total 135 minutes
- Introduction•20 minutes
- Jumping from the Logistic Function to Logistic Regression•20 minutes
- Training a Logistic Regression Model Using Gradient Descent•20 minutes
- Predicting Ad Click-Through with Logistic Regression Using Gradient Descent•15 minutes
- Training a Logistic Regression Model with Regularization•20 minutes
- Training on Large Datasets with Online Learning•10 minutes
- Handling Multiclass Classification•15 minutes
- Implementing Logistic Regression Using TensorFlow•15 minutes
1 assignment•Total 10 minutes
- Logistic Regression and Feature Engineering Fundamentals•10 minutes
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.
What's included
1 video7 readings1 assignment
1 video•Total 1 minute
- Predicting Stock Prices with Regression Algorithms - Overview Video•1 minute
7 readings•Total 120 minutes
- Introduction•15 minutes
- Getting Started with Feature Engineering•10 minutes
- Acquiring Data and Generating Features•15 minutes
- How Does Linear Regression Work?•20 minutes
- Implementing Linear Regression with Scikit-learn•20 minutes
- Implementing Decision Tree Regression•15 minutes
- Implementing a Regression Forest•25 minutes
1 assignment•Total 10 minutes
- Regression Techniques in Financial Forecasting•10 minutes
In this section, we cover building and optimizing neural networks for stock price prediction using activation functions, dropout, and early stopping.
What's included
1 video6 readings1 assignment
1 video•Total 1 minute
- Predicting Stock Prices with Artificial Neural Networks - Overview Video•1 minute
6 readings•Total 115 minutes
- Introduction•20 minutes
- Backpropagation•15 minutes
- Implementing Neural Networks from Scratch•20 minutes
- Implementing Neural Networks with PyTorch•20 minutes
- Early Stopping•20 minutes
- Fine-tuning the Neural Network•20 minutes
1 assignment•Total 10 minutes
- Neural Networks in Financial Forecasting•10 minutes
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.
What's included
1 video10 readings1 assignment
1 video•Total 1 minute
- Mining the 20 Newsgroups Dataset with Text Analysis Techniques - Overview Video•1 minute
10 readings•Total 135 minutes
- Introduction•10 minutes
- NLP Applications•15 minutes
- Corpora•20 minutes
- NER•10 minutes
- Getting the Newsgroups Data•10 minutes
- Exploring the Newsgroups Data•10 minutes
- Counting the Occurrence of Each Word Token•15 minutes
- Reducing Inflectional and Derivational Forms of Words•10 minutes
- t-SNE for Dimensionality Reduction•15 minutes
- Building Embedding Models Using Shallow Neural Networks•20 minutes
1 assignment•Total 10 minutes
- Exploring Text Analysis with the 20 Newsgroups Dataset•10 minutes
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.
What's included
1 video7 readings1 assignment
1 video•Total 1 minute
- Discovering Underlying Topics in the Newsgroups Dataset with Clustering and Topic Modeling - Overview Video•1 minute
7 readings•Total 105 minutes
- Introduction•10 minutes
- Getting Started with K-Means Clustering•20 minutes
- Implementing k-Means with scikit-learn•20 minutes
- Clustering Newsgroups Data Using K-Means•15 minutes
- Describing the Clusters Using GPT•10 minutes
- Discovering Underlying Topics in Newsgroups•10 minutes
- Topic Modeling Using LDA•20 minutes
1 assignment•Total 10 minutes
- Exploring Text Data Analysis Techniques•10 minutes
In this section, we explore SVM for face recognition, analyze hyperplane separation in high-dimensional data, and apply PCA to enhance image classification performance.
What's included
1 video5 readings1 assignment
1 video•Total 1 minute
- Recognizing Faces with Support Vector Machine - Overview Video•1 minute
5 readings•Total 105 minutes
- Introduction•20 minutes
- Handling Outliers•20 minutes
- Multiclass Cases in Scikit-learn•25 minutes
- Choosing Between Linear and RBF Kernels•20 minutes
- Building an SVM-Based Image Classifier•20 minutes
1 assignment•Total 10 minutes
- Exploring SVM Techniques and Applications•10 minutes
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.
What's included
1 video8 readings1 assignment
1 video•Total 1 minute
- Machine Learning Best Practices - Overview Video•1 minute
8 readings•Total 120 minutes
- Introduction•10 minutes
- Best Practice 4 Dealing with Missing Data•20 minutes
- Best practice 5 – Storing large-scale data•10 minutes
- Best Practice 10 Deciding Whether to Rescale Features•15 minutes
- TF and TF-IDF•15 minutes
- Best practices in the model training, evaluation, and selection stage•15 minutes
- Best Practice Reducing Overfitting•15 minutes
- Saving and Restoring Models Using Pickle•20 minutes
1 assignment•Total 10 minutes
- Machine Learning Data Preparation Essentials•10 minutes
In this section, we explore CNNs for clothing image classification, focusing on building blocks, model design, and data augmentation techniques to enhance performance.
What's included
1 video5 readings1 assignment
1 video•Total 1 minute
- Categorizing Images of Clothing with Convolutional Neural Networks - Overview Video•1 minute
5 readings•Total 105 minutes
- Introduction•10 minutes
- The Pooling Layer•25 minutes
- Classifying Clothing Images with CNNs•20 minutes
- Fitting the CNN Model•25 minutes
- Rotation for Data Augmentation•25 minutes
1 assignment•Total 10 minutes
- Exploring Convolutional Neural Networks for Clothing Image Classification•10 minutes
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.
What's included
1 video7 readings1 assignment
1 video•Total 1 minute
- Making Predictions with Sequences Using Recurrent Neural Networks - Overview Video•1 minute
7 readings•Total 110 minutes
- Introduction•15 minutes
- One-to-many RNNs•20 minutes
- Analyzing and Preprocessing the Data•20 minutes
- Building a Simple LSTM Network•15 minutes
- Revisiting Stock Price Forecasting with LSTM•10 minutes
- Writing Your Own War and Peace with RNNs•20 minutes
- Building and Training an RNN Text Generator•10 minutes
1 assignment•Total 10 minutes
- Exploring Sequence Modeling with RNNs•10 minutes
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.
What's included
1 video7 readings1 assignment
1 video•Total 1 minute
- Advancing Language Understanding and Generation with the Transformer Models - Overview Video•1 minute
7 readings•Total 120 minutes
- Introduction•10 minutes
- Attention Score Calculation and Embedding Vector Generation•25 minutes
- Multi-head Attention•10 minutes
- Positional Encoding•20 minutes
- Fine-tuning a Pre-trained BERT Model for Sentiment Analysis•20 minutes
- Using the Trainer API to Train Transformer Models•15 minutes
- Writing Your Own Version of War and Peace with GPT•20 minutes
1 assignment•Total 10 minutes
- Exploring Transformer Architecture and Applications•10 minutes
In this section, we cover CLIP for image and text retrieval, focusing on contrastive learning and zero-shot classification.
What's included
1 video7 readings1 assignment
1 video•Total 1 minute
- Building an Image Search Engine Using CLIP a Multimodal Approach - Overview Video•1 minute
7 readings•Total 110 minutes
- Introduction•15 minutes
- Zero-shot Image Classification•10 minutes
- Getting Started with the Dataset•20 minutes
- Vision Encoder•15 minutes
- CLIP Model•10 minutes
- Obtaining Embeddings for Images and Text to Identify Matches•25 minutes
- Zero-shot Classification•15 minutes
1 assignment•Total 10 minutes
- Multimodal Models in Image Search•10 minutes
In this section, we cover decision-making in complex environments using reinforcement learning.
What's included
1 video8 readings1 assignment
1 video•Total 1 minute
- Making Decisions in Complex Environments with Reinforcement Learning - Overview Video•1 minute
8 readings•Total 150 minutes
- Introduction•20 minutes
- Cumulative Rewards•10 minutes
- Simulating the FrozenLake Environment•25 minutes
- Solving FrozenLake with the Value Iteration Algorithm•20 minutes
- Solving FrozenLake with the Policy Iteration Algorithm•20 minutes
- Simulating the Blackjack Environment•20 minutes
- Performing On-Policy Monte Carlo Control•15 minutes
- Introducing the Q-Learning Algorithm•20 minutes
1 assignment•Total 10 minutes
- Reinforcement Learning Fundamentals•10 minutes
Instructor
Why people choose Coursera for their career
Frequently asked questions
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.
More questions
Financial aid available,