Deep learning concepts explained visually, including neural networks, CNNs, LSTMs, Transformers, diffusion models, and representation learning.
Learning area
These pages are grouped as a learning collection. More lecture notes, examples, and practical tools can be added without changing the page structure.
Available resources
Available resources
This category combines current MuhammadLab pages that match the topic. More lecture guides and interactive tools can be added here as the lab grows.
Upload an image and inspect CNN channels, padding, convolution kernels, ReLU, pooling, normalization, and step-by-step calculations.
Learn CNN-style image convolution with preset kernels, a custom 3x3 matrix editor, pixel-grid calculations, and local image filtering.
Learn the diffusion idea: add noise, denoise step-by-step, and how text-to-image works at a high level.
Understand Transformers with self-attention intuition, why they scale, and common model variants (encoder/decoder).
Learn convolution, kernels/filters, pooling, feature maps, and why CNNs work for images.
Learn how ViT uses patches + attention for vision tasks and how it differs from CNNs.
Learn how LSTMs use gates and a memory cell to handle longer dependencies in sequence data.