Description
In this course, you will :
- Understand the fundamentals of linear algebra and calculus, which are critical mathematical subjects at the heart of machine learning and data science.
- Manipulate tensors with NumPy, TensorFlow, and PyTorch, the three most important Python tensor libraries.
- All of the necessary vector and matrix operations for machine learning and data science.
- Using eigenvectors, SVD, and PCA, reduce the dimensionality of complex data to the most informative elements.
- Solve for unknowns using both basic (e.g., elimination) and advanced techniques (e.g., pseudoinversion).
- Learn how calculus works from the ground up with interactive Python code demos.
- Understand advanced differentiation rules such as the chain rule intimately.
- Hand-calculate the partial derivatives of machine-learning cost functions, as well as using TensorFlow and PyTorch.
- Understand exactly what gradients are and why they are necessary for ML via gradient descent.
- Calculate the area under any given curve using integral calculus.
- Be able to comprehend the nuances of cutting-edge machine learning papers more thoroughly.
- Understand what happens beneath the hood of machine learning algorithms, including those used for deep learning.
Syllabus :
- Data Structures for Linear Algebra
- Tensor Operations
- Matrix Properties
- Eigenvectors and Eigenvalues
- Matrix Operations for Machine Learning
- Limits
- Derivatives and Differentiation
- Automatic Differentiation
- Partial Derivative Calculus
- Integral Calculus
- Probability