Iñigo Parra

[ˈiɲiɣo ˈpara]

Portrait of Iñigo Parra

San Francisco, CA

Short Manim animations of ideas in deep learning

Sinusoidal Position Encodings

Demonstrating how sinusoidal positional encodings work in transformer models

Query, Key, and Value

Visualizing the Query, Key, and Value matrices in attention mechanisms

The GAN Objective

Breaking down the mathematical formulation of Generative Adversarial Networks