Skip to content

vinayshanbhag/math

Repository files navigation

A collection of Jupyter notebooks...

To explore mathematical concepts behind machine learning algorithms and understand their inner working. Code is intentionally sub-optimal.

The Discrete Cosine Transform: Understanding the Discrete Cosine Transform (DCT)

Expectation–Maximization in Gaussian Mixture models: Expectation–Maximization in 1D Gaussian Mixture model using numpy

k-means clustering: Explore the math behind k-means, an unsupervised clustering algorithm, and understand its limitations.

Univariate Linear Regression: Univariate Linear Regression in numpy

Affine Transformations: Visualizing affine transformations in numpy

Convolution Kernels: Convolution matrices in image filtering applications

Eigen Decomposition: Eigen Values and Vectors

Principal Component Analysis: Principal Component analysis with numpy

Linear Discriminant Analysis: Linear Discriminant Analysis with numpy

Fourier Analysis: Fourier analysis with numpy and scipy

Norm: Euclidean, Taxicab and other vector norms

Projection Profile: Correcting document skew for imaging and machine learning applications

Prime Spirals: Visualizing prime numbers on a polar plot (Ulam spirals). 3blue1brown's video at https://www.youtube.com/watch?v=EK32jo7i5LQ&feature=share

Weierstrass Function: A pathological real valued function that is continuous everywhere, yet differentiable nowhere

Interpolation: Interpolation using scipy.interpolate

LaTeX: LaTeX markdown quick reference for use in these notebooks