Deep Learning Mindset, Boundaries, and Setup
help learners understand when deep learning is worth using and when it is not.
Advanced Deep Learning with PyTorch
A responsible PyTorch portfolio with tensors, autograd, training loops, CNNs, transfer learning, embeddings, transformers, diagnostics, and a model card.
Tensors, Shapes, Datasets, and DataLoaders
make learners fluent with the data structures used by neural networks.
Autograd, Loss, Backpropagation, and Training Loops
demystify how neural networks learn.
Feed-Forward Networks for Structured Data
connect neural networks to familiar tabular modelling problems.
Optimization, Initialization, Normalization, and Regularization
teach why training can fail and how to diagnose it.
Convolutional Neural Networks for Images
introduce computer vision through small, understandable models.
Transfer Learning and Fine-Tuning for Vision
show how pretrained models change the deep learning workflow.
Embeddings, Sequences, and Attention Intuition
prepare learners for transformer workflows without jumping too fast.
Transformers for Text Classification and Feature Extraction
teach practical transformer use while keeping claims honest.
Representation Learning and Embedding Workflows
connect deep learning representations to retrieval and clustering ideas.
Diagnostics, Interpretability, Robustness, and Responsible Use
prevent learners from trusting neural networks too quickly.
Capstone Deep Learning Portfolio and Model Card
bring the course together into a responsible final project.
First-release boundary
This is a text-first course shell. Leonardo/image creation, external review, learner pilot evidence, and production publication remain separate later tasks.