Self-Attention

Multi-Head Attention

Comparison of CNN and ViT

Vision Transformer

Diffusion Models Explained with Math From Scratch

Greetings

Supervised Learning

Unsupervised Learning

Semi-Supervised Learning

Self-Training

Self-Supervised Learning

Autoencoder

Logit and Probability

Binary Classification

Multi-Class Classification

Multi-Label Classification

Multi-Class vs. Multi-Label Classification

Loss Function

Cost Function

Binary Cross-Entropy Loss

Categorical Cross-Entropy Loss

Linear Transformation

Affine Transformation

Projective Transformation

Homogeneous Coordinates

Rigid Transformation

Similarity Transformation

Forward and Backward Image Warping

Splatting

Image Rotation