This course teaches learners how to apply transfer learning techniques to improve data efficiency in machine learning models. The course covers methods such as hybrid instance-based transfer learning and differentially private aggregation approaches. The goal is to enable participants to solve real-world business problems, including the cold-start problem, by transferring knowledge from existing datasets to new target tasks. The intended audience for this course includes data scientists, machine learning engineers, and professionals looking to enhance their machine learning skills and improve model performance in data-limited scenarios. The teaching method involves a combination of theoretical explanations, mathematical justifications, and practical examples to demonstrate the application of transfer learning concepts in practice.
Data Efficiency Through Transfer Learning - Eddie Du
Overview
Syllabus
Intro
About Georgian Partners
Proposed Solution: Data Aggregation with Transfer Learning
Instance-based Transfer Learning
Mathematical Justification
Bluecore's Challenge: Binary classification while preserving privacy
Proposed Solution: Aggregate at the Model level
What does it mean to preserve privacy?
First attempt at preserving privacy
Revisiting the Compensation Example
Quantifying Privacy with Differential Privacy
Differential Privacy in Machine Learning
Using Differential Privacy in Practice
Recall the Proposed Solution for Bluecore
Differentially Private Logistic Regression
Effect of Epsilon on Performance
Summary
Taught by
Open Data Science
