Scribd
Upload
3 views

INT255 Unit 1

The presentation covers the fundamentals of linear algebra essential for machine learning, including vectors, matrices, and linear transformations. It explains key concepts such as vector operations, vector spaces, basis and dimension, and norms, which are crucial for data representation and optimization in machine learning applications. Additionally, it highlights the applications of these mathematical concepts in various machine learning techniques like regularization and clustering algorithms.

Uploaded by

kannareddyp.2004
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as KEY, PDF, TXT or read online on Scribd
3 views

INT255 Unit 1

The presentation covers the fundamentals of linear algebra essential for machine learning, including vectors, matrices, and linear transformations. It explains key concepts such as vector operations, vector spaces, basis and dimension, and norms, which are crucial for data representation and optimization in machine learning applications. Additionally, it highlights the applications of these mathematical concepts in various machine learning techniques like regularization and clustering algorithms.

Uploaded by

kannareddyp.2004
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as KEY, PDF, TXT or read online on Scribd
You are on page 1/ 14

Lovely Professional University

Department of Computer Science & Engineering


Presentation on
INT255 :MATHEMATICS BEHIND MACHINE LEARNING UNIT-1

Presented By:
Abhinav Singh
Department of Machine Learning
Topics to be covered…
Fundamentals of Linear Algebra
Vectors and Matrices
Vector Space Concepts
Linear Transformations
Norms and Spaces
Introduction to Linear Algebra
Essential for Machine Learning Applications
Mathematical representation of data structures
Key: Vectors, Matrices, Spaces, Transformations
Foundation for optimization and modeling
Interprets multi-dimensional datasets easily
Core to computer vision techniques
Vectors
Quantities with magnitude and direction
Represented as rows or columns
Used in data points representation
Example: [3, 4], 2D vector
Originates from linear coordinate space
Core in numerical machine calculations
Vectors Operations
Addition: Sum components in order
Dot product: A * B scalar operation
Produce orthogonal hyperplanes dimensions.
Example : set k=3
Matrices
Matrices are rectangular arrays of numbers.
Used for transformations
Representing linear equations in ML.
Example, we have two matrices A and B
A = [1 ,2] B = [5,6]
[3, 4] [7, 8]
C = [1 + 5 2+6] C = [6 8]
[3+ 7 4+8] ==> [10 12]
Matrices operations
Example, we have two matrices A and B
Vector Space
Set of Vectors
Closed under Addition
Closed under Scalar Multiplication
Zero Vector
Additive Inverse
Basis and Dimension
Basis vectors span spaces,
Define vector space dimensions.
Basis simplifies transformations
Number of Vectors in a Basis
Intrinsic Property of the Space
Not Dependent on the Chosen Basis
Linear Transformations
Mapping between two vector spaces
Takes vector as input and transforms
Additivity and scalar multiplication are preserved
Visualizing Linear TransformationsGeometric
interpretationRotations, scaling, shearingTransformations in 2D
and 3D
Properties of Transformations
Preserve vector addition and scalar multiplication.
Characterized by matrices
Simplify complex computations.
Linearity
Additivity: T(u + v) = T(u) + T(v)
Homogeneity: T(cu) = cT(u)
Invertibility
One-to-one and onto
Inverse transformation exists
Matrix representation is invertible
Norms - Measuring Magnitude
Measure of vector magnitude
Defines distance in vector spaces
Key concept in optimization
L1 Norm (Manhattan Distance)
Sum of absolute values of components
Distance traveled along axes
L2 Norm (Euclidean Distance)
Square root of sum of squared components
Straight-line distance
Applications in Machine Learning
Regularization
Loss functions
Support Vector Machines (SVM)
Clustering algorithms

You might also like