Reading History
Continue where you left off in your study vault.
Recent
Linear Algebra Basics
Vectors, matrices, and operations fundamental to deep learning.
View Note
Attention Mechanism
The core innovation behind transformers — scaled dot-product attention.
View Note
Convolutional Neural Networks
CNNs for spatial data — convolutions, pooling, and architectures.
View Note
Automatic Differentiation
How frameworks like PyTorch compute gradients automatically.
View Note
Multilayer Perceptrons
The building block of deep learning — fully connected neural networks.
View Note