Dropout as Shared-Parameter Bagging
March 7, 2026
A concrete way to understand dropout in deep learning: sampled subnetworks with shared weights, standing in for a much more expensive ensemble.
Read postDeep Learning
Posts on deep learning concepts, textbook notes, regularization, and the structural assumptions behind neural networks.
3 posts currently filed under Deep Learning.
Representation, Efficiency, and Learnability
February 15, 2026
Goodfellow Chapter 6 sharpened how I separate representation, parameter efficiency, and optimization when thinking about deep feedforward networks.
Read post
Math Foundations for Deep Learning
February 7, 2026
Part I of Goodfellow, Bengio, and Courville works best as shared vocabulary for later chapters, with proof details still worth supplementing.
Read post