Fin Irjmets1653474126

e-ISSN: 2582-5208
International Research Journal of Modernization in Engineering Technology and Science

( Peer-Reviewed, Open Access, Fully Refereed International Journal )
Volume:04/Issue:05/May-2022 Impact Factor- 6.752 www.irjmets.com
MACHINE LEARNING APPROACH FOR LINEAR ALGEBRA
Dr. Kalaivazhivijayaragavan*1, Abinisha.K*2, Dhara.T*3, Santhiya.E*4
*1Associate Professor, Department Of Information Technology, Anjalai Ammal Mahalingam
Engineering College, Thiruvarur, Tamilnadu, India.
*2,3,4Students,
B.Tech., Final Year, Department Of Information Technology, Anjalai Ammal
Mahalingam Engineering College, Thiruvarur, Tamilnadu, India.
ABSTRACT
This project we are planning to implement the mathematical concept using python that we will encounter in
data science and machine learning career quite frequently. Three main pillars of machine learning model are
Data, Machine Learning Module and training module. Machine learning and mathematics correlation are as
follows; The concepts of linear algebra is used for developing algorithms in machine learning. It connects the
Machine Learning algorithms to run on a huge number of dataset. Our project helps to understand the best way
to get familiar with the concepts of Mathematics in Machine Learning Algorithm. Which helps to understand of
mathematics is paramount and to enable to come up with machine learning solutions for the real world
problems.
Keywords: Linear Algebra, vectors, Matrices, Accuracy.
I. INTRODUCTION
Machine learning is the science of programming machine to think and act like humans without being
specifically programmed do. We already use machine learning in our daily life without knowing it. Email spam
recognition, spell check even the You tube video recommendation which brought you here are implemented
using machine learning. Machine learning uses algorithm to learn tasks these algorithms are fed with data
which they learn to perform these tasks. This means that over time as changes in data occur we don’t need to
reprogram our application just let it find patterns and learn from the new data. Machine learning is the subset
of artificial intelligence which is a science concerned with imparting human –like intelligence into machines and
creating a machine which can Sense , Reason , Act , Adapt. Deep learning is a sub branch of machine learning
which is inspired by working of the human brain. Machine learning is leading us to a future where machine can
learn and think. Model Selection in machine learning is the process of choosing the best suited model for a
particular problem. Selecting a model depends on various factors such as dataset, task, nature of the model etc.,
In this work we will focus only on creating a new machine model for mathematics. Mathematics consists of
linear algebra including Vectors, Matrices, Norms, Broadcasting.
II. LINEAR ALGEBRA MODEL
Building a linear algebra model of a system is to identify and describe the various cause and effect relationships
between the system parameters, decision variable, and state variables and to define and evaluate the system
performance. To determine the system parameters is a part of the formulation of a model of the system. The
events of the model of the system are artificially generated using the decision variables and system parameters
and as an effect changes in the state-variables are recorded and the system performance criterion is estimated.
III. MACHINE LEARNING PROCESS
1. Data collection
In this step, we try to collect the data from different sources with respect to our problem statement. It is
important collect good quantity and quality data
2. Data preparation
We make sure that we refine and simplify our data. so that ML model can easily process and understand that
data. we have to split the data into training set and testing set.
3. Model selection
It is based on our type of data we have to select the appropriate and most suitable model for our project.
www.irjmets.com @International Research Journal of Modernization in Engineering, Technology and Science

[3842]
e-ISSN: 2582-5208
4. Model training
Whatever data we have split into the training set that we have to pass our ml model can understand about the
data get the insights of the data.
5. Prediction
Predicting a missing or unknown value based on current or past data
6. Evaluation
We evaluate our trained ml model with the help pf test set of data, whatever remaining test set of data that we
will use to evaluate our ML model and to check that how accurate is performing.
IV. LINEAR ALGEBRA

Machine Learning is one of the applications of Artificial Intelligence (AI) that provides systems, the ability to
automatically learn and improve from experience without being explicitly programmed. Machine Learning is
used to develop the computer programs that can access data and use it learn for themselves. Linear algebra is a
branch of mathematics that can be used in science and engineering. It helps in understanding and working of
machine learning, algorithms, specially in deep learning. simple machine learning algorithm derived using
knowledge of machine learning .Linear algebra will be dealing with vectors and matrix. The understanding of
vectors and matrix is really important because all the computation are based on this kind of vectors and matrix
A feature vector is a vector whose entries represent the “feature of some object.

[3843]
e-ISSN: 2582-5208
V. CONCEPT OF LINEAR ALGEBRA
Vectors
Linear algebra Matrices

Norms
Vectorization
Vectors
Vectors are one dimensional array of numbers these are typically denoted in lower case, italics, bold. Vectors
are arranged in an order, so element can be accessed by its index. Vectors are representing a particular point in
space.Vectors of length two represents location in 2D matrix, length of three represent location in 3D cube,
length of n represents location in n dimensional tensor.
Matrix
Matrix is a well arranged array of objects . A can contain any number or any function as its elements and each
unique data (any number, symbol or expression) is called the element of the matrix. Matrix has different
number of columns and rows.
Norms
Norms is a quantity that describes the size of the vector it measures simple (euclidean) distance from origin.
Most common norm in machine learning is instead of ||x||2, it can be denoted as ||x||.
Vectorization
Vectorization which is a technique of speeding up our computations especially for deep learning algorithms
where we are dealing with huge number of data so there can be multiple ways of doing the computations The
one way would be that you convert the data into form of matrices and vectors and instead of using explicit for
loop and doing scalar calculation
VI. NEURAL NETWORK FOR LINEAR ALGEBRA
This operations can be compute the output for the first and only hidden layer of the above neural network. Let’s
break it down. Every single column of this network is vectors. Vectors act as dynamic arrays that can be used to
collect the data. In the current neural network, the vector ‘x’ holds the input. It is not necessary to represent
inputs as vectors but if you do so, they become increasingly convenient to perform operations in parallel.
[3844]
e-ISSN: 2582-5208
VII. CONCLUSION
In this paper the application of Mathematics in Machine Learning Algorithms and their working. Hence in our
project we reason out of Machine Learning is important. This paper tells how the mathematical concept to
introduced Machine Learning algorithms that can be used to solve the task with accuracy.
VIII. REFERENCES
[1] Gennady Grabarnik, Luiza Kim-Tyan, Serge Yaskolko, “Addressing Prerrequisited for STEM Classes
Using an Example of Linear Algebra for a Course in Machine Learning”, The Twelfth International
Conference on Mobile, Hybrid, and On-line Learning, 2020, pp. 21_26
[2] Anzt Hartwig, Dongarra Jack, Flegar Goran and S. Enrique, "Quintana-Orti. Variable-Size Batched LU for
Small Matrices and Its Integration into Block-Jacobi Preconditioning", 2017 46th International
Conference on Parallel Processing (ICPP), pp. 91-100, 2017.
[3] Markus Hegland and Paul E. Saylor, "Block jacobi preconditioning of the conjugate gradient method on
a vector processor", International Journal of Computer Mathematics, vol. 44, no. 1–4, pp. 71-89, 1992.
[4] S. Bhowmick, V. Eijkhout, Y. Freund, E. Fuentes, and D. Keyes. Application of machine learning to the
selection of sparse linear solvers. Int. J. High Perf. Comput. Appl., 2006. submitted.
[5] Xiao-Chuan Cai and Marcus Sarkis. A restricted additive Schwarz preconditioner for general sparse
linear systems. SIAM J. Sci. Comput., 21:792-797, 1999.
[6] Erika Fuentes. Statistical and Machine Learning Techniques Applied to Algorithm Selection for Solving
Sparse Linear Systems. PhD thesis, University of Tennessee, Knoxville TN, USA, 2007.
[7] T.A. Manteuffel. An incomplete factorization technique for positive definite linear systems. Math.
Comp., 34:473-497, 1980.
[8] Henk van der Vorst. Bi-CGSTAB: a fast and smoothly converging variant of Bi-CG for the solution of
nonsymmetric linear systems. SIAM J. Sci. Stat. Comput., 13:631-644, 1992.
[9] David C. Wilson, David B. Leake, and Randall Bramley. Case-based recommender components for
scientific problem-solving environments. In Proceedings of the Sixteenth International Association for
Mathematics and Computers in Simulation World Congress, 2000.
[10] N. Kyrtatas and D. G. Spampinato, "A Basic Linear Algebra Compiler for Embedded Processors", 2015
Design Automation Test in Europe Conference Exhibition (DATE), pp. 1054-1059, 2015.

[3845]

Fin Irjmets1653474126

Uploaded by

Copyright:

Available Formats

Fin Irjmets1653474126

Uploaded by

Document Information

Original Title

Copyright

Available Formats

Share this document

Share or Embed Document

Sharing Options

Did you find this document useful?

Is this content inappropriate?

Copyright:

Available Formats

Fin Irjmets1653474126

Uploaded by

Copyright:

Available Formats

e-ISSN: 2582-5208

International Research Journal of Modernization in Engineering Technology and Science

www.irjmets.com @International Research Journal of Modernization in Engineering, Technology and Science

IV. LINEAR ALGEBRA

www.irjmets.com @International Research Journal of Modernization in Engineering, Technology and Science

Linear algebra Matrices

www.irjmets.com @International Research Journal of Modernization in Engineering, Technology and Science

You might also like