Understand data science for machine learning
- Offered byMicrosoft
Understand data science for machine learning at Microsoft Overview
Duration | 7 hours |
Total fee | Free |
Mode of learning | Online |
Schedule type | Self paced |
Difficulty level | Beginner |
Official Website | Explore Free Course  |
Credential | Certificate |
Understand data science for machine learning at Microsoft Course details
- Introduction to machine learning
- Build classical machine learning models with supervised learning
- Introduction to data for machine learning
- Train and understand regression models in machine learning
- Refine and test machine learning models
- Create and understand classification models in machine learning
- Select and customize architectures and hyperparameters using random forest
- Confusion matrix and data imbalances
- Measure and optimize model performance with ROC and AUC
- Microsoft Learn provides several interactive ways to get an introduction to classic machine learning
- These learning paths will get you productive on their own, and also are an excellent base for moving on to deep learning topics
- From the most basic classical machine learning models, to exploratory data analysis and customizing architectures, youâ??ll be guided by easy to digest conceptual content and interactive Jupyter notebooks, all without leaving your browser
- Youâ??ll be introduced to some essential concepts, explore data, and interactively go through the machine learning life-cycle - using Python to train, save, and use a machine learning model like we would in the real world
- Through content and exercises, we explore how to understand your data, how to encode it so that the computer can interpret it properly, how to clean it of errors, and tips that will help you create models that perform well
- This learning material takes a dive into some common regression analyses, both simple and more complex, and provides some insight on how to assess model performance
Understand data science for machine learning at Microsoft Curriculum
Introduction to machine learning
Introduction
What are machine learning models?
Exercise - Create a machine learning model
What are inputs and outputs?
Exercise - Visualize inputs and outputs
How to use a model
Exercise - Use machine learning models
Knowledge check
Summary
Build classical machine learning models with supervised learning
Introduction
Define supervised learning
Exercise - Implement supervised learning
Minimize model errors with cost functions
Exercise - Optimize a model by using cost functions
Optimize models by using gradient descent
Exercise - Implement gradient descent
Knowledge check
Summary
Introduction to data for machine learning
Introduction
Good, bad, and missing data
Exercise - Visualize missing data
Examine different types of data
Exercise - Work with data to predict missing values
One-hot vectors
Exercise - Predict unknown values using one-hot vectors
Knowledge check
Summary
Train and understand regression models in machine learning
Introduction
What is regression?
Exercise - Train a simple linear regression model
Multiple linear regression and R-squared
Exercise - Train a multiple linear regression model
Polynomial Regression
Exercise - Polynomial regression
Knowledge check
Summary
Refine and test machine learning models
Introduction
Normalization and standardization
Exercise - Feature scaling
Test and training datasets
Exercise - Test and train datasets
Nuances of test sets
Exercise - Test set nuances
Knowledge check
Summary
Create and understand classification models in machine learning
Introduction
What are classification models?
Exercise - Build a simple logistic regression model
Assessing a classification model
Exercise - Assessing a logistic regression model
Improving classification models
Exercise - Improving classification models
Knowledge check
Summary
Select and customize architectures and hyperparameters using random forest
Introduction
Decision trees and model architecture
Exercise - Decision trees and model architecture
Random forests and selecting architectures
Exercise - Selecting random forest architectures
Hyperparameters in classification
Exercise - Hyperparameter tuning with random forests
Knowledge check
Summary
Confusion matrix and data imbalances
Introduction
Confusion matrices
Exercise - Building a confusion matrix
Data imbalances
Exercise - Resolving biases in a classification model
Cost functions versus evaluation metrics
Exercise - Multiple metrics and ROC curves
Knowledge check
Summary
Measure and optimize model performance with ROC and AUC
Introduction
Analyze classification with receiver operator characteristic curves
Exercise - Evaluate ROC curves
Compare and optimize ROC curves
Exercise - Tune the area under the curve
Knowledge check
Summary
Understand data science for machine learning at Microsoft Entry Requirements
- None
- Not mentioned
Other courses offered by Microsoft
Student Forum
Anything you would want to ask experts?
Data ScienceMachine LearningMachine Learning and Pattern RecognitionUnderstand data science for machine learning