Introduction

This guide is a comprehensive record of my journey through the Deep Learning course this semester. It aims to bridge the gap between complex mathematical theories and practical implementations, serving as both a personal knowledge base and a roadmap for others in the field.

What This Guide Covers

• Basic Mathematics for deep learning
• Linear Models
• Multilayer perceptrons, Model selection, Regularization
• Training neural network, Optimization, Numerical stability
• Convolutional neural network with applications
• Sequence models, Recurrent neural network
• Attention
• Self-supervised learning
• Generative models
• Learning with fewer labeled examples
• Graph Neural Network
• Reinforcement learning