Machine Learning

KernelPCA vs. PCA for Dimensionality Reduction

...explained with visuals.

Oct 15 •

A Memory-efficient Technique to Train Large Models

...that even LLMs like GPTs and LLaMAs use.

Oct 14 •

Breathing KMeans vs KMeans

Robustify KMeans with centroid addition and removal.

Oct 7 •

Activation Pruning for Model Compression (with implementation)

Removing 74% neurons with 0.5% accuracy drop.

Oct 2 •

What is Contrastive Learning?

A popular ML interview question, explained with a use case.

Sep 25 •

L2 Regularization is NOT Just a Regularization Technique

A lesser-known usage of L2 regularization.

Sep 19 •

The Ideal Loss Function for Class Imbalance

...a popular ML interview question.

Sep 18 •

How Dropout Actually Works

A lesser-known detail of Dropout.

Sep 10 •

6 Graph Feature Engineering Techniques

Must-know for building GNNs.

Jul 31 •

2 Techniques to Synchronize ML Models in Multi-GPU Training

...explained visually.

Jul 10 •

DropBlock vs. Dropout for Regularizing CNNs

Addressing a limitation of Dropout when used in CNNs.

Jul 9 •

A Hands-on Demo on Autoencoders

...along with applications.

Jul 8 •

#nojs-banner { position: fixed; bottom: 0; left: 0; padding: 16px 16px 16px 32px; width: 100%; box-sizing: border-box; background: red; color: white; font-family: -apple-system, "Segoe UI", Roboto, Helvetica, Arial, sans-serif, "Apple Color Emoji", "Segoe UI Emoji", "Segoe UI Symbol"; font-size: 13px; line-height: 13px; } #nojs-banner a { color: inherit; text-decoration: underline; } This site requires JavaScript to run correctly. Please turn on JavaScript or unblock scripts