Machine Learning - The Bare Math Behind Libraries

Übersicht

Explore the mathematical foundations of machine learning, from supervised to unsupervised learning techniques, to gain a deeper understanding of neural networks and their underlying processes.

Lehrplan

• Introduction to Machine Learning Mathematics
Overview of Machine Learning and Mathematical Prerequisites
Linear Algebra Basics: Vectors, Matrices, and Operations
Probability and Statistics Fundamentals
• Supervised Learning Foundations
Linear Regression: Least Squares, Cost Function, and Gradient Descent
Logistic Regression: Sigmoid Function, Loss Function, and Maximum Likelihood
Support Vector Machines: Margin, Dual Formulation, and Kernel Trick
• Unsupervised Learning Techniques
Clustering Algorithms: K-Means and Hierarchical Clustering
Principal Component Analysis (PCA): Eigenvectors and Eigenvalues
Gaussian Mixture Models and Expectation-Maximization
• Neural Networks and Deep Learning
Perceptron Model and Multilayer Perceptrons
Backpropagation and Chain Rule of Calculus
Activation Functions: Sigmoid, ReLU, and Softmax
• Optimization and Training Techniques
Stochastic Gradient Descent and Variants
Learning Rate Schedules and Regularization Techniques
Overfitting and Underfitting: Bias-Variance Tradeoff
• Advanced Topics in Machine Learning
Convolutional Neural Networks: Convolutions, Pooling, and Leveraging Image Data
Recurrent Neural Networks: Time Series and Sequence Data
Introduction to Reinforcement Learning Basics
• Mathematical Exploration of Performance and Evaluation
Confusion Matrix, Precision, Recall, and F1 Score
Receiver Operating Characteristic (ROC) and AUC
Cross-Validation and Model Selection Strategies
• Course Conclusion and Capstone Project
Integrating Mathematical Concepts in Real-world Applications
Building a Simple Machine Learning Model From Scratch
Discussing Future Trends and the Role of Mathematics in Advancing AI

---

Fachgebiete

Conference Talks