
Dropout as Implicit Bagging in Deep Learning
March 7, 2026
A concrete way to understand dropout in deep learning: shared-parameter ensemble training that approximates bagging without training separate models.
Read postBook notes from Alex Leung, with a focus on deep learning, machine learning foundations, and technical reading.
3 posts currently filed under Book Notes.

A concrete way to understand dropout in deep learning: shared-parameter ensemble training that approximates bagging without training separate models.
Read post
Chapter 6 sharpened how I think about architecture as a structural assumption, not just a tuning choice.
Read post
A short review of Part I of Goodfellow, Bengio, and Courville's Deep Learning textbook, focused on the mathematical foundations.
Read postCopyright © 2020 - 2026 Alex Leung