Scribd
Upload
5 views13 pages

Machine Learning

Uploaded by

Mariam Mubashhir
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
5 views13 pages

Machine Learning

Uploaded by

Mariam Mubashhir
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
You are on page 1/ 13

Role of Mathematics

MACHINE
LEARNING
WHAT IS MACHINE
LEARNING?
Machine learning is a subfield of
artificial intelligence, which is
broadly defined as the
capability of a machine to
imitate intelligent human
behavior.
MATHEMATICS IN MACHINE
LEARNING
PROBABILI STATISTIC
TY S

ML
LINEAR
CALCULU
ALGEBRA
S
STATISTI
CS
Statistics are tools to get answers to questions about
data:
• What is Common?
• What is Expected?
• What is Normal?
• What is the Probability?

Tendency :• The Mean


• The Median
• The Mode
Variability :• Variance
• Deviation
• Range
• interquatile range
PROBABILITY
DISTRIBUTION
tells us the likelihood of different outcomes.

Normal Binomial Poisson Exponential Multinomial

• Data Understanding • Bayesian Inference


• Modeling Uncertainty • Sampling and
Simulation
WHAT IS DIFFERENTIAL
CALCULUS?
How Does Differential
Calculus Contribute to
Machine Learning?
By analyzing the derivatives of
the model’s performance with
respect to its parameters,
machine learning algorithms can
decide the course wherein to
regulate those parameters to
gain higher results
CALCULUS : GRADIENT
• It help DESCENT
determine how to adjust a model's parameters to
minimize errors.
• Diff erent calculus used for gradient descent enables machine
learning models to learn from data and make accurate
predictions..

• For simple models, adjustments


are made to the slope and
intercept, and plotting errors
for diff erent parameter values
often results in a U-shaped
curve, known as a convex
curve...
• When combining individual errors, the model produces a three-dimensional
convex diagram. This shape refl ects the weight space defi ned by the range of
possible model weights
LINEAR ALGEBRA : DATA
REPRESENTATION
• E a c h d a t a s e t re s e m b l e s a t a b l e - l i ke s t r u c t u re c o n s i s t i n g o f
ro w s a n d c o l u m n s . W h e re e a c h ro w re p re s e n t s o b s e r v a t i o n s ,
a n d e a c h c o l u m n re p re s e n t s f e a t u re s / Va r i a b l e s . T h i s d a t a s e t i s
h a n d l e d a s a M a t r i x , w h i c h i s a ke y d a t a s t r u c t u re i n L i n e a r
Algebra

• In machine learning, images/photographs are used for computer vision applications.


• a. g e i s a n e x a m p l e o f t h e m a t r i x f ro m l i n e a r a l g e b r a b e c a u s e a n i m a g e i s a
Each Im
t a b l e s t r u c t u re c o n s i s t i n g o f h e i g h t a n d w i d t h f o r e a c h p i xe l .
Matrix Factorization
• Matrix factorization is a way of breaking down a large matrix (a grid
of numbers) into simpler, smaller matrices. This process helps to
simplify complex data.

• For example, in a
recommendation system like
Netfl ix, matrix factorization
can help predict which
movies you might like by
breaking down user
preferences and movie
characteristics into simpler
components.
Real Life Application in ML
• FACIAL RECOGNITION : People previously received name
suggestions for their mobile photos and Facebook tagging, but now
someone is immediately tagged and verified by comparing and
analyzing patterns through facial contours.

• PRODUCT RECOMMENDATIONS : machine learning can get eerily


accurate by finding hidden relationships in data and predicting what
you want before you know you want it. If the data is incomplete,
sometimes you may end up with an offbase recommendation

• EMAIL AUTOMATION : While your inbox seems relatively boring,


machine learning influences its function behind the scenes. Email
automation is a direct result of successful machine learning,

https://www.tableau.com/learn/articles/machine-learning-examples
CONCLUSION
• Mathematics serves as the backbone of ML
algorithms and models, empowering machines
to process, analyze, and interpret vast amounts
of data.
• Concepts from linear algebra, calculus,
probability theory, and statistics are essential
for developing machine learning algorithms.
• These algorithms use mathematical equations
and functions to identify patterns, make
predictions, and classify information.
BIBLIOGRA
PHY
https://blog.bytescrum.com/probability-distributions-in-machine-lear
ning
https://www.w3schools.com/ai/ai_statistics.asp
https://www.scribbr.com/statistics/variability/
https://www.geeksforgeeks.org/role-of-differential-calculus-in-machi
ne-learning/
https://www.javatpoint.com/linear-algebra-for-machine-learning
https://www.geeksforgeeks.org/ml-linear-algebra-operations/
https://www.javatpoint.com/linear-algebra-for-machine-learning
https://www.semanticscholar.org/paper/Application-of-Matrix-in-Ima
ge-Compression-Chandra/56658a8d6084b39b60eb966602675d67fa
0d730c

You might also like