https://github.com/ricardorobledo/ml_calculus
https://github.com/ricardorobledo/ml_calculus
matplotlib numpy pandas python3 sympy
Last synced: 6 months ago
JSON representation
- Host: GitHub
- URL: https://github.com/ricardorobledo/ml_calculus
- Owner: RicardoRobledo
- Created: 2025-07-17T23:47:01.000Z (7 months ago)
- Default Branch: main
- Last Pushed: 2025-07-17T23:53:32.000Z (7 months ago)
- Last Synced: 2025-07-18T04:26:55.011Z (7 months ago)
- Topics: matplotlib, numpy, pandas, python3, sympy
- Language: Jupyter Notebook
- Homepage:
- Size: 147 KB
- Stars: 0
- Watchers: 0
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# Calculus for Machine Learning Notebook
This notebook is based on Calculus for ML book available at [machinelearningmastery.com](https://machinelearningmastery.com/). It covers fundamental and advanced topics.
## Key Topics Covered
- **Limits and continuity:** understanding function behavior near points, formal definitions, and practical examples
- **Derivatives of functions:** basics of differentiation, power, product, quotient, and chain rules
- **Derivatives of common functions:** including sine and cosine, with examples and computational tools
- **Multivariate calculus:** partial derivatives, gradient vectors, Jacobian and Hessian matrices, and their significance in ML
- **Optimization fundamentals:** unconstrained and constrained optimization, Lagrange multipliers, and applications in ML models
- **Taylor series and approximations:** polynomial approximations of functions to simplify complex models
- **Gradient descent and learning:** iterative methods to minimize loss functions in ML
- **Calculus in neural networks:** understanding backpropagation and gradient computation for training
- **Support Vector Machines (SVM):** mathematical formulation and optimization using calculus tools
This notebook combines theoretical explanations with practical examples to provide a solid foundation in calculus concepts that are critical for developing and understanding machine learning models.