0% found this document useful (0 votes)

29 views8 pages

14 K - Nearest Neighbours

Uploaded by

siddsathe1012

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

0% found this document useful (0 votes)

29 views8 pages

14 K - Nearest Neighbours

Uploaded by

siddsathe1012

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/ 8

K-Nearest Neighbors

K-nearest neighbors
● K-nearest neighbors is known as knn.
● Knn is the simplest algorithm for supervised machine learning.
● Knn stores all the available data and classify the new data points based on similarity.
● It can be used in both task regression and classification.but it usually prefer to use in
classification.
● It is used to find pattern recognition,intrusion detection and data mining.

A wonderful serenity
Why do we need K-NN
K-Nearest Neighbours is a simple algorithm that stores all available data and classifies new cases based on a similarity measure . It classifies
the new data points on the basis of distance .
For Ex ::

Suppose we have two class , class A and Class B .

Class A is yellow in colour and Class B is purple in color
Now New Data point/Class which is red in colour .
So you calculate the distances of your new data with all the others to know
which ones have the smallest distance, so you get 3 (or 6) of the closest data and
check which class that appears most , in the case of the image below, the closest
data to the new data are those that are inside the first circle (inside circle), and
inside this circle there are 3 other data (already classified with yellow), we will
check which is the predominant class in there, look, it’s purple, because there
are 2 purple balls and only 1 yellow, so this new data that before was not
classified, now it will be classified as purple.
K-NN Working
K-NN working can be explanation ;
● Find the value of K i.e. the nearest data points. K can be any integer value
● Calculate the distance between test data and each row of training data with the
help of any of the method like ( Euclidean, Manhattan or Hamming distance ).
But we generally used Euclidean distance
● Now based on the distance value, sort them in ascending order. .
● Now , choose the top K row from the shorted array/data point .
● Then assign the top class/category to the test data point .
● Our model is Ready .
How select the value of K in K-NN ?
○ There is no rule to determine the value of K so we try some random values . To find the best result of it .
○ But the most preferable value of K is 5 .

○ A very low value like K=1 or K=2 ,K=3 may cause of outliers and make noisy our data
○ A large value may good but that may also cause some difficulties .
Advantages of K-NN.
● It is versatile algorithm can be used for regression and classification task.
● It is simple to implement and intuitive to learn .
● Single hyper parameters which makes easy to tune the model.
● No Training time for classification it simples tags the new data entry based on historical data.
● Variety of distance criteria to choose from like euclidean,manhattan and minkowski distance.
Disadvantages of K-NN.
● Knn does not work well with large dataset because calculating the distance among all the data will be very costly,
● Does not work well with high dimensionality of data
● It is very sensitive to noisy data and missing data.
● Data needs to normalized and standardized properly.

* * For implementation refer code file

Thank
You...

K-Nearest Neighbor (KNN) Algorithm For Machine Learning
No ratings yet
K-Nearest Neighbor (KNN) Algorithm For Machine Learning
17 pages
K-Nearest Neighbor (KNN) Algorithm For Machine Learning - Javatpoint
No ratings yet
K-Nearest Neighbor (KNN) Algorithm For Machine Learning - Javatpoint
18 pages
12 ML KNN
No ratings yet
12 ML KNN
28 pages
K-NN Algorithm and Clustering Analysis
No ratings yet
K-NN Algorithm and Clustering Analysis
93 pages
K-Nearest Neighbors
No ratings yet
K-Nearest Neighbors
35 pages
Week 7 Part 1KNN K Nearest Neighbor Classification
No ratings yet
Week 7 Part 1KNN K Nearest Neighbor Classification
47 pages
CSL0777 L22
No ratings yet
CSL0777 L22
35 pages
Lecture 14 and 15
No ratings yet
Lecture 14 and 15
42 pages
21 KNN
No ratings yet
21 KNN
28 pages
KNN HMM
No ratings yet
KNN HMM
51 pages
Supervised Learning KNN
No ratings yet
Supervised Learning KNN
23 pages
E Learning KNN
No ratings yet
E Learning KNN
31 pages
Distance-Based Methods - KNN
No ratings yet
Distance-Based Methods - KNN
8 pages
K-Nearest NEIGHBOUR
No ratings yet
K-Nearest NEIGHBOUR
16 pages
K-Nearest Neighbor Algorithm
100% (1)
K-Nearest Neighbor Algorithm
6 pages
Unit V: Distance and Rule Based Models
No ratings yet
Unit V: Distance and Rule Based Models
56 pages
KNN
No ratings yet
KNN
53 pages
Unit V Non Parametric Machine Learning
No ratings yet
Unit V Non Parametric Machine Learning
47 pages
23 Supervised KNN
No ratings yet
23 Supervised KNN
18 pages
Machine Learning
No ratings yet
Machine Learning
32 pages
ML Unit-2
No ratings yet
ML Unit-2
24 pages
K Nearest Neighbors KNN A Fundamental Machine Learning Algorithm
No ratings yet
K Nearest Neighbors KNN A Fundamental Machine Learning Algorithm
11 pages
K - Nearest Neighbor
No ratings yet
K - Nearest Neighbor
22 pages
Lecture Note #3 - PEC-CS701E
No ratings yet
Lecture Note #3 - PEC-CS701E
27 pages
Machine Learning Unit-3.1
No ratings yet
Machine Learning Unit-3.1
20 pages
K-Nearest Neighbor (KNN)
No ratings yet
K-Nearest Neighbor (KNN)
27 pages
Seminar Report File On KNN Models: University Institute of Engineering and Technology, Kurukshetra University
No ratings yet
Seminar Report File On KNN Models: University Institute of Engineering and Technology, Kurukshetra University
24 pages
Clustering - KNN
No ratings yet
Clustering - KNN
10 pages
KNN - Feb 19
No ratings yet
KNN - Feb 19
42 pages
1694600817-Unit2.3 KNN CU 2.0
No ratings yet
1694600817-Unit2.3 KNN CU 2.0
25 pages
K-Nearest Neighbor (KNN)
No ratings yet
K-Nearest Neighbor (KNN)
12 pages
'Machine Learning (Nagarjun)
No ratings yet
'Machine Learning (Nagarjun)
10 pages
K-Nearest Neighbor
No ratings yet
K-Nearest Neighbor
22 pages
K Nearest Neighbors
No ratings yet
K Nearest Neighbors
22 pages
Intro To KNN
No ratings yet
Intro To KNN
8 pages
K-Nearest Neighbor Classification-Algorithm and Characteristics
No ratings yet
K-Nearest Neighbor Classification-Algorithm and Characteristics
6 pages
Supervised Example KNN
No ratings yet
Supervised Example KNN
22 pages
Introduction To KNN
100% (1)
Introduction To KNN
8 pages
K - Nearest Neighbor
No ratings yet
K - Nearest Neighbor
13 pages
What Is KNN
No ratings yet
What Is KNN
9 pages
K-Nearest Neighbors (K-NN) Algorithm
No ratings yet
K-Nearest Neighbors (K-NN) Algorithm
10 pages
K Nearest Neighbor: Presented by
No ratings yet
K Nearest Neighbor: Presented by
29 pages
KNN
No ratings yet
KNN
9 pages
K-Nearest Neighbors (KNN) Algorithm in Machine Learning
No ratings yet
K-Nearest Neighbors (KNN) Algorithm in Machine Learning
3 pages
Algorithms - K Nearest Neighbors
No ratings yet
Algorithms - K Nearest Neighbors
23 pages
K Nearest Neighbor (KNN)
No ratings yet
K Nearest Neighbor (KNN)
9 pages
Why Do We Need A K-NN Algorithm?
No ratings yet
Why Do We Need A K-NN Algorithm?
11 pages
K-Nearest Neighbor (KNN) Algorithm For Machine Learning
No ratings yet
K-Nearest Neighbor (KNN) Algorithm For Machine Learning
3 pages
K Nearestneighborknnalgorithm 241117075907 d767c46d
No ratings yet
K Nearestneighborknnalgorithm 241117075907 d767c46d
13 pages
Bài nhóm tìm hiểu về KNN
No ratings yet
Bài nhóm tìm hiểu về KNN
5 pages
Miss Erum Mahood Topic: KNN Algorthim: Presentator BY: Zobia Malaika Maryam Minahil
No ratings yet
Miss Erum Mahood Topic: KNN Algorthim: Presentator BY: Zobia Malaika Maryam Minahil
10 pages
Lecture 38 KNN
No ratings yet
Lecture 38 KNN
4 pages
Experiment No 7 ML
No ratings yet
Experiment No 7 ML
4 pages
K-Nearest Neighbor (KNN) : Non-Parametric Algorithm
No ratings yet
K-Nearest Neighbor (KNN) : Non-Parametric Algorithm
7 pages
Day43 KNN Intro
No ratings yet
Day43 KNN Intro
4 pages
Unit 3 KNN
No ratings yet
Unit 3 KNN
16 pages
K-Nearest Neighbor Algorithm
No ratings yet
K-Nearest Neighbor Algorithm
6 pages
KNN Algorithm
No ratings yet
KNN Algorithm
2 pages
6 - KNN Classifier
No ratings yet
6 - KNN Classifier
10 pages

Note: This service is not intended for secure transactions such as banking, social media, email, or purchasing. Use at your own risk. We assume no liability whatsoever for broken pages.

14 K - Nearest Neighbours

Uploaded by

14 K - Nearest Neighbours

Uploaded by

K-Nearest Neighbors

Suppose we have two class , class A and Class B .

* * For implementation refer code file

You might also like

Pfad - The Proxy pFad of © 2024 Garber Painting. All rights reserved.