Deep Learning Theory

This repository contains practical implementations of core deep learning theory concepts.
The code is based on my learning journey through various online courses, including:

• Udemy
• AIVN (AI Vietnam)
• ProtonX by Coursemind

The goal of this repository is to consolidate theoretical knowledge into hands-on code examples, covering topics such as:

• Math fundamentals for deep learning
• Machine learning algorithms: Linear Regression, Logistic Regression, Softmax Regression
• Neural network architectures (MLP, CNN, RNN, LSTM)
• Optimization techniques and loss functions
• And more...

Folder Structure

This repository is organized into modules that reflect different aspects of deep learning theory:

• 01_numpy/: Introduction to NumPy – array operations, broadcasting, and matrix computations.
• 02_mathematics/: Mathematical foundations for deep learning, including:
  • 2.1_calculus/: Derivatives, gradients, chain rule, and backpropagation concepts.
  • 2.2_linear_algebra/: Matrix operations, vector spaces, eigenvalues/eigenvectors, and their applications in neural networks.
  • 2.3_probabilities/: Basic probability theory, distributions, and concepts used in probabilistic models and Bayesian learning.