Deep Learning

Neural networks, architectures, and training techniques for deep models.

Core concepts of neural networks, backpropagation, and deep learning basics.

Convolutional Networks

CNNs, convolution operations, pooling, and architectures for spatial data.

Sequence Models

RNNs, LSTMs, GRUs, and architectures for sequential and temporal data.

Transformers & Attention

Self-attention, transformer architecture, and the foundation of modern AI.

Generative Adversarial Networks

GANs, adversarial training, and generative modeling with neural networks.

Graph Neural Networks

GNNs, message passing, and learning on graph-structured data.

Training Techniques

Learning rate schedules, regularization, normalization, and optimization tricks.

Variational autoencoders, denoising, sparse, and learned latent representations.

Self-Supervised Learning

Contrastive learning, masked prediction, BYOL, and learning without labels.

Neural Architecture Search

AutoML, NAS algorithms, and automated model design.

Energy-Based Models

Boltzmann machines, EBMs, score matching, and energy landscapes.