Scribd
Upload
12 views12 pages

Bayes Decision Theorylect3

Uploaded by

riya.munjal.ug21
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
12 views12 pages

Bayes Decision Theorylect3

Uploaded by

riya.munjal.ug21
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/ 12

Bayes decision theory

What Is Bayesian Decision


Theory?
• Bayesian Decision Theory (BDT) refers to the statistical
method that uses the Bayes Theorem to determine
conditional probabilities. It forecasts the result by
considering the current circumstances in addition to past
data. In other words, it is a classification method that
applies the Bayes Theorem to produce results.

• In pattern recognition, BDT is used to identify and


classify patterns into different categories. In machine
learning, BDT is used to train machine learning models
on predictions.
• Decision theory, which is applied to a wide range of human
endeavors, examines the logic and mathematics aspects of
decision-making under ambiguity. A large portion of it
employs concepts, methods, and formalisms that fall under
the Bayesian theory, which is a statistical method used to
update our knowledge and beliefs as one receives new
information. It evaluates the risk (i.e., cost) of allocating an
input to a specific class, and it uses probability to make
classifications.
• Bayesian Decision Theory (BDT) is a statistical tool that helps
determine conditional probabilities using the Bayes Theorem.
• Bayes’ Theorem is a mathematical formula that outlines the
relationship between the probability of one event happening,
the probability of another event happening, and the
probability of both events happening together.
• When the probability structure of categories is known
perfectly, the optimal Bayes classifier for comparison
with other classifiers can be determined. Bayes
classifiers are trained to assess data and determine the
probability of different categories. A key benefit of a
perfectly known probability structure is that it allows
analysts to predict errors when generalizing to novel
patterns.
• Bayesian decision theory in pattern recognition and
Bayesian decision theory in machine learning are well-
known areas of BDT application.
Applications
• Bayes’ theorem is a fundamental principle in probability theory
and statistics that establishes a relationship between
conditional probabilities. It helps update our knowledge,
notions, or beliefs about the likelihood of an event happening
based on existing and new evidence.
• This mathematical formula finds extensive applications in diverse
fields, including medical diagnosis, search engine usage, weather
forecasting, A/B testing, fault diagnosis, and stock market
analysis.
• n medical diagnoses, Bayes’ theorem calculates the likelihood of
a specific disease or condition given certain symptoms or test
results. It calculates the posterior probability, which refers to
ascertaining the probability of a medical condition or disease
based on the symptoms.
• The posterior probability refers to the updated
probability of an event obtained by applying the new
evidence formed. Its basics are underpinned by
conditional probability and Bayes’ theorem.
• The formula for calculations is P(A|B) = P(B|A)*P(A)/P(B)
• The important elements are prior probability P(A),
evidence P(B), P(B|A) is the likelihood function.
• Some applications specifically related to machine learning
have been enumerated below.
• The email spam filtering function uses this mathematical
formula to classify inbound emails as spam or legitimate
by detecting and interpreting the presence of specific
words or patterns.
• Document categorization uses Bayes’ theorem to assign
documents to predefined categories by evaluating the
probability of a document belonging to a specific category.
• Fraud detection systems employ Bayes’ theorem to assess
the probability of a transaction or claim being fraudulent
by studying the relevant risk factors and historical data.
advantages of Bayesian
Decision Theory
• Handling uncertainty,
– Incorporating prior knowledge,
– Updating beliefs with new evidence, and
– Providing a framework for decision-making.
It also helps decision-makers assess risks and benefits,
leading to informed and optimal decisions.
• Marginal Probability
• When we usually talk about probability of an event, it is the marginal probability we
are concerned with. In other words, it is the probability of an event irrespective of any
other factor/event/circumstance. Basically, you ‘marginalize’ other events and hence
the name. It is denoted by P(A) and read as “probability of A”.

• Conditional Probability
• Conditional probability is when the occurence of an event is wholly or partially
affected by other event(s). Alternatively put, it is the probability of occurrence of an
event A when an another event B has already taken place. It is denoted by P(A|B) and
read as “probability of A given B”.

• Joint Probability
• Joint probability is calculated when we are interested in the occurrence of two
different events simultaneously. It is also often referenced as probability of
intersection of two events. It is denoted by P(A, B) and read as “probability of A and
B”.
Derivation of Bayes’ Theorem:
• A model can be viewed as any one of the process, relationship,
equation or an approximation to understand and describe the
data.
• We know from the conditional probability:
• P(A|B) = P(A, B) / P(B)
• => P(A, B) = P(A|B) * P(B) ... (i)
• Similarly,
• P(A, B) = P(B|A) * P(A) ... (ii)
• From equation (i) and (ii):
• P(A|B) * P(B) = P(B|A) * P(A)
• => P(A|B) = [P(B|A) * P(A)] / P(B)
For each sample input, it calculates its posterior and assign it to the class corresponding to the
maximum value of the posterior probability.

You might also like