Scribd
Upload
5 views

Assignment 2 A I

Uploaded by

mohdavaish93
Copyright
© © All Rights Reserved
Available Formats
Download as PDF, TXT or read online on Scribd
5 views

Assignment 2 A I

Uploaded by

mohdavaish93
Copyright
© © All Rights Reserved
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 3

Assignment 2(Artificial inteligence)

Submitted by submitted to:

Name: Mohammad Avash Khan. Shra Fatima mam


Branch: Btech CSE B. (Assistant professor)
year/sem: 3rdsth
enrollment:2200101+0t

QL Explain the process of learning decision trees and discuss


its significance in inductive learning.
|Learning Decision Trees:

Data Collection: First, data is gathered, inclucing the set of


features and the corresponding outcomes.

Tree Construction The decision tree algorithm starts by


choosing the best attribute (feature) to split the dataset
based on a metric ike Gini impurity or Intormation Gain. This
process divides the dataset into subsets that are more
|homogeneous concerning the targct variable.

Recursive Splitting: The splitting process continues


recursively on cach subSet, choosing the next best attribute
|for each split until the data is completely classified or meets
la stopping condition (eg. max tree depth).
Tree Pruning: Once the treeeis fully grown pruning techniques
are applied to remove branches that have little significance,
Ireducing overfitting and improving generalzation.

Significance in hductive Learning: Decision trees are crucial in


inductive learning as they generalize from specific examples,
capturing patterns ard relatiorships in the data They are
interpretable, making them useful in domains where
understanding model decisions is essential. Decision trees also
support learing in diverse applications lke medical diagnoses
credit scoring. and traud detection.

Q2. Describe the proces5 of forward and back ward chaining in


propositional calculus. How are they used in logical agents for
krowledge inference?

Forward Chaining:

Starts with known facts and applies inference rules to


derive new facts until reaching the goal.

lt's a data-driven appro3ch where each rule whose premises


are true leads to the addition of its conclusion to the
krowledge base.
Backward Chaining:

Begins with the goal and works backward. attempting to find


Supporting facts.

This goal-driven approach checks if the goal can be satisfied


by fraing rules that support it andreoursively verifes cach
premise.

|Use in Logical Agents: Logical agents use these chaining


Imethods to perform automated reasoning:
Forward Chaining: Usetul tor situations where we have a set
of known facts and aim to explore potential outcomes (eg.
diagnosis systerms).
Backward Chaining: Used when there is a specific goal to
prove or disprove based on the knowledge base,like inexpert
systems.

You might also like