Lessons
16 lessons are ready.
- Introduction to Deep Learning
- Mathematical Foundations I (Linear Algebra)
- Mathematical Foundations II (Probability & Information Theory)
- Training Neural Networks: Core Concepts
- Optimization Techniques
- Dimensionality Reduction & Autoencoders
- Regularization and Training Tricks
- Weight Initialization & Training Improvements
- Word & Sequence Representation
- Convolutional Neural Networks (CNNs)
- Recurrent Neural Networks (RNNs) & Sequence Models
- Transformers & Modern Sequence Modeling
- Deep Generative Models: VAEs, GANs, and Diffusion Models
- Graph Neural Networks: The Hop Budget
- Deep Reinforcement Learning: Explore, Then Pay
- Transfer Learning: The Donor Floor