0% found this document useful (0 votes)
7 views1 page

Key Search Algorithms in AI

The document outlines key search algorithms including A* Search, BFS, DFS, Minimax with Alpha-Beta Pruning, Hill Climbing, and Constraint Satisfaction Problems (CSP). It provides definitions, algorithms, comparisons, and examples for each topic, emphasizing their importance in exams and real-world applications. Notably, A* and CSP have appeared in both the 2022-23 and 2023-24 exams.
Copyright
© All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
0% found this document useful (0 votes)
7 views1 page

Key Search Algorithms in AI

The document outlines key search algorithms including A* Search, BFS, DFS, Minimax with Alpha-Beta Pruning, Hill Climbing, and Constraint Satisfaction Problems (CSP). It provides definitions, algorithms, comparisons, and examples for each topic, emphasizing their importance in exams and real-world applications. Notably, A* and CSP have appeared in both the 2022-23 and 2023-24 exams.
Copyright
© All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd

ChatGPT

Search Algorithms (Unit 2):


A* Search (Algorithm, 8-puzzle problem - ABSOLUTELY CRITICAL,
appeared in both 2022-23 and 2023-24 long questions).
Breadth-First Search (BFS) & Depth-First Search (DFS): Algorithms,
comparisons, completeness, optimality, applications.
Minimax and Alpha-Beta Pruning: Concepts, working with game
trees.
Hill Climbing (Steepest Ascent, Local Maxima, Plateaus, Ridges,
limitations).
Constraint Satisfaction Problem (CSP): Definition, examples (e.g.,
graph
coloring, 8-queens), solving techniques. (Appeared in both 2022-23
and
2023-24 long questions).
Easy and good answer explain

Sure! Here's a simple, clear, and exam-ready explanation for Unit 2: Search Algorithms based on your
syllabus. I'll explain each topic briefly but thoroughly, with key points and examples to help you write
good answers in the exam.

1. A Search Algorithm*
Definition:
A* (A-Star) is an informed search algorithm that finds the shortest path from a start state to a goal state
using a heuristic.

Algorithm:
A* uses:

g(n): Cost from start to current node n

h(n): Heuristic estimate of cost from n to goal

f(n) = g(n) + h(n)

It always expands the node with the lowest f(n) value.

8-Puzzle Problem:
A 3x3 board with tiles numbered 1 to 8 and one blank space.
Goal: Arrange tiles in order by sliding them.

Heuristics:

h1(n): Number of misplaced tiles

h2(n): Manhattan Distance (better)

Example:
Initial State:

Copy code

1 2 3
4 5
6 7 8

Use A* to find shortest sequence to goal:

Copy code

1 2 3
4 5 6
7 8

Why Important:
Appeared in 2022–23 and 2023–24 exams.

A* is complete and optimal if the heuristic is admissible (never overestimates).

2. BFS & DFS


Breadth-First Search (BFS):
Explores level by level

Uses a queue (FIFO)

Complete and Optimal (if all step costs are equal)

Time & Space Complexity: O(b^d)

Depth-First Search (DFS):


Explores deepest node first

Uses a stack (LIFO) or recursion

Not optimal, not complete (may get stuck in infinite loop)

Time: O(b^d), Space: O(bd)

Comparison:
Feature BFS DFS

Data Structure Queue Stack

Complete Yes No

Optimal Yes No

Time/Space O(b^d) O(bd)

Applications Shortest path Game trees

3. Minimax & Alpha-Beta Pruning


Minimax:
Used in 2-player games (e.g., chess, tic-tac-toe)

Maximizer tries to win

Minimizer tries to block

Builds a game tree, calculates the best move by backtracking.

Alpha-Beta Pruning:
Improves Minimax by eliminating unnecessary branches.

Alpha = Best value for Maximizer

Beta = Best value for Minimizer

If a branch cannot affect the final decision, cut it off (prune it).

Benefits:
Same result as Minimax

More efficient

4. Hill Climbing
Definition:
A local search algorithm that moves in the direction of increasing value (like going uphill).

Variants:
Steepest-Ascent: Chooses the best neighbor

Simple: Takes the first better neighbor

Random-Restart: Tries multiple times to escape local maxima

Problems:
Local Maxima: Peak that is not the highest

Plateau: Flat area, hard to choose direction

Ridges: Need diagonal move, but can’t detect

5. Constraint Satisfaction Problems (CSP)


Definition:
Problem where the goal is to find values for variables that satisfy constraints.

Examples:
Graph Coloring: Color each node such that no adjacent nodes have same color.

8-Queens: Place 8 queens on chessboard such that no two attack each other.

Solving Techniques:
1. Backtracking Search

2. Forward Checking – Eliminate values that violate constraints early.

3. Constraint Propagation – e.g., AC-3 Algorithm

4. Heuristics:

Minimum Remaining Values (MRV)

Degree Heuristic

Least Constraining Value

Why Important:
Common in AI exams and real-world problems.

Appeared in 2022–23 and 2023–24.

Ask anything

Tools

ChatGPT can make mistakes. Check important info. See Cookie Preferences.

You might also like