Machine Learning Explainability
In this Guided Project, we will walk through explainability techniques for various types of machine learning models like linear regression, light gradient boosting machine, CNNs, and pre-trained transformers.
4.3 (50 Reviews)
Language
- English
Topic
- Machine Learning
Enrollment Count
- 396
Skills You Will Learn
- Data Science, Python, Machine Learning, Deep Learning
Offered By
- IBM
Estimated Effort
- 45 minutes
Platform
- SkillsNetwork
Last Update
- April 30, 2024
Explainability refers to having an understanding of why a model makes a certain prediction. This typically comes in form of knowing the relationship between a model's prediction and the input features used to generate said prediction (text, pixels, features, etc.). Linear models like linear regression, and ensemble models like decision trees are known to be easily interpretable. Deep learning models are black boxes, which makes it much harder to understand how those models make predictions. In this Guided Project, we will use SHAP, a common model-agnostic explainability method, to calculate the contributions of each feature to the prediction for various types of models.
A Look at the Project Ahead
After completing this guided project you will be able to:
- Use LinearExplainer to explain linear models like linear regression
- Use TreeExplainer to explain ensemble models like light gradient boosting machine
- Use GradientExplainer to explain CNN models
- Use SHAP Explainer to explain pre-trained transformer models
This course mainly uses Python and JupyterLabs. Although these skills are recommended prerequisites, no prior experience is required as this Guided Project is designed for complete beginners.
Frequently Asked Questions
Your Instructor
Kopal Garg
I am a Data Scientist Intern at IBM, and a Masters student in computer science at the University of Toronto. I am passionate about building AI-based solutions that improve various aspects of human life.
Language
- English
Topic
- Machine Learning
Enrollment Count
- 396
Skills You Will Learn
- Data Science, Python, Machine Learning, Deep Learning
Offered By
- IBM
Estimated Effort
- 45 minutes
Platform
- SkillsNetwork
Last Update
- April 30, 2024
Instructors
Kopal Garg
Data Scientist Intern at IBM
I am a Data Scientist Intern at IBM, and a Masters student in Computer Science at the University of Toronto. I am passionate about building data science, and machine learning-based systems for improving various aspects of life.
Read moreContributors
Joseph Santarcangelo
Senior Data Scientist at IBM
Joseph has a Ph.D. in Electrical Engineering, his research focused on using machine learning, signal processing, and computer vision to determine how videos impact human cognition. Joseph has been working for IBM since he completed his PhD.
Read moreSam Prokopchuk
Software Engineer, Data Scientist Intern
Software Engineer/Data Scientist Intern at IBM.
Read moreSvitlana Kramar
Data Scientist
I’m a passionate data science educator whose goal is to learn by teaching innovative data science tools that can improve our day-to-day tasks and our quality of life. My interests are in Natural Language Processing: text classification, summarization, and generation. Research can take a long time because there are a lot of resources and new opinions posted every day. Having tools to summarize and extract the information can save a lot of time. I hope we can all learn, approve, and apply the data science tools to cut down on the repetitive and tedious tasks, to make more informed decisions in life, to differentiate fake from real, and to open communication spaces to language-diverse or hearing-impaired audiences. The applications are limitless! My personality: I am a foodie and I love cooking and learning different cuisines. I also love travelling and connecting with people by learning a little bit of their language, about their food and music. I hold Data Science and Analytics master’s degree, specializing in Machine Learning, from University of Calgary.
Read more