Machine Learning and Deep Learning Maths - Matrix and Vector Operations

Overview

This course teaches learners how to perform various matrix and vector operations using Python for machine learning and deep learning applications. The learning outcomes include understanding element-wise operations, creating matrices and vectors, calculating additions and subtractions, converting between dense and sparse matrices, transposing matrices, and computing statistical measures like mean, variance, and standard deviation. Students will also learn about dot products, matrix ranks, traces, determinants, reshaping matrices, inverting matrices, and selecting elements from vectors and matrices. The course uses a hands-on teaching method with inline Python functions to demonstrate these mathematical concepts. The intended audience for this course is individuals interested in machine learning, deep learning, and data science who want to strengthen their mathematical foundations for these fields.

Syllabus

Element-wise Operation using Inline Function - Python | What are Inline Functions in Python?.
Machine Learning Mathematics - Create Matrix using Python.
Machine Learning Mathematics - Create Vectors using Python.
Calculate Matrix Addition and Subtraction using Python.
Calculate Matrix Size Shape & Dimension using Python.
Dense to Sparse Matrix conversion using Python.
Machine Learning Mathematics - Matrix Transpose using Python.
18.Mean Variance and Std Deviation of a matrix.
17.Convert dictionary into matrix.
16.Dot product of two vectors.
15.Rank of a matrix.
14.Trace of a matrix.
13.Flattening a matrix.
12.Determinant of a matrix.
11.Find Max and Min element from Matrix.
10.Diagonal of a matrix.
9.Invert a matrix.
8.Reshape a matrix.
7. Select an element from vector and matrix.