Which of the following is a clustering algorithm in machine learning

K-Means Clustering Algorithm

K-Means is one of the most popular clustering algorithms that is used in machine learning. This algorithm aims to group similar data points together and create clusters. This algorithm works by randomly selecting data points and assigning them to clusters. The data points are then assigned to the cluster that has the closest mean.


K-Means is a clustering algorithm that is a commonly used machine learning technique. The goal of K-Means is to cluster data points together so that they are similar to one another. K-Means is an unsupervised learning algorithm, which means that it does not require labels in order to learn.

K-Means works by first randomly initializing K cluster centers. Then, each data point is assigned to the nearest cluster center. After that, the cluster centers are updated to be the mean of the data points assigned to them. This process is repeated until the cluster centers do not change or a pre-determined threshold is reached.

One of the advantages of K-Means is that it is very fast and scalable. However, one of the disadvantages is that it can get stuck in local optima and it does not work well with high dimensional data.

How the K-Means Clustering Algorithm Works

The K-means clustering algorithm is a method of vector quantization, originally from signal processing, that aims to partition n observations into k clusters in which each observation belongs to the cluster with the nearest mean. This results in a partitioning of the data space into Voronoi cells.

The objective of the K-means algorithm is to find:

the set of k cluster centroids
U= {u1,…,uk}, such that
the within-cluster sum of squares (WCSS) is minimized:

WCSS(U) = ∑i=1k∑x∈Ci||x−ui||2

Advantages and Disadvantages of K-Means Clustering

There are a few advantages and disadvantages to using the k-means clustering algorithm that you should be aware of before you decide to use it for your own data sets.


-One of the biggest advantages of k-means clustering is that it is very fast and efficient, especially when working with large data sets.
-Another advantage is that it is relatively easy to implement and understand, compared to other clustering algorithms.
-K-means clustering can also be used to initialize other more sophisticated machine learning algorithms.


-One of the biggest disadvantages of k-means clustering is that it can be sensitive to outliers in the data set. This can cause the algorithm to produce suboptimal results.
-Another disadvantage is that k-means clustering can only be used with numeric data. This means that if you have categorical data, you will need to use another clustering algorithm.

Fuzzy C-Means Clustering Algorithm

Fuzzy c-means (FCM) is a data clustering technique in machine learning where data points are grouped together into clusters. It is a type of soft clustering, where each data point can belong to more than one cluster. The algorithm is also called the ISODATA clustering algorithm.


Fuzzy c-means (FCM) is a data clustering technique similar to k-means clustering, with the difference being that in FCM, each data point can belong to more than one cluster. FCM is often used in image segmentation.

The algorithm works by minimizing the following objective function:

where is a weighting factor ( typically between 1.5 and 3.0), is the membership matrix, is the centroid matrix, is the TransformedDistance matrix, and represents the cardinality of the set . The TransformedDistance matrix contains the squared distances between each data point and each centroid. The cardinality of a set is the number of elements in that set.

How the Fuzzy C-Means Clustering Algorithm Works

The Fuzzy C-Means Clustering Algorithm (FCM) is a machine learning algorithm that is used to cluster data points into a chosen number of clusters. The algorithm works by assigning each data point a membership value for each cluster, which is then used to calculate the centroid (mean) of each cluster. The FCM algorithm is an iterative process, meaning that it repeats the clustering process until it converges on a final solution.

The FCM algorithm has a number of advantages over other clustering algorithms, including its ability to handle data sets with non-uniform densities and its flexibility in the number of clusters that can be output. Additionally, the FCM algorithm is relatively fast and efficient, making it well suited for large data sets.

Advantages and Disadvantages of Fuzzy C-Means Clustering

-Allows for data points to belong to more than one cluster (thus “fuzzy”)
-Cluster boundaries can be more accurately estimated
-Can be used with both numerical and categorical data

-Complicated algorithm that is difficult to understand and implement
-Slow runtime compared to other clustering algorithms

Hierarchical Clustering Algorithm

Hierarchical clustering is a type of unsupervised machine learning algorithm used to cluster groups of data points. It is a bottom-up approach where each data point is treated as a single cluster and then merged with other clusters as the algorithm progresses. The final clusters are then represented as a tree-like structure.


Clustering is a type of unsupervised learning that groups data points together based on similarity. Clustering algorithms are used in a variety of applications, such as customer segmentation, image compression, and healthcare.

There are many different types of clustering algorithms, but the most common ones are hierarchical clustering and k-means clustering.

Hierarchical clustering is a type of clustering algorithm that groups data points into clusters, where each cluster is represented by a single point (called a centroid). The centroid is the mean of all the data points in the cluster.

Hierarchical clustering algorithms can be either agglomerative (bottom-up) or divisive (top-down). Agglomerative algorithms start by assigning each data point to its own cluster, and then repeatedly merge two clusters until all data points are in one cluster. Divisive algorithms start by putting all data points into one cluster, and then repeatedly split the cluster into two until each data point is in its own cluster.

The most popular agglomerative hierarchical clustering algorithm is called single-linkage clustering, while the most popular divisive hierarchical clustering algorithm is called k-means clustering.

Single-linkage clustering groups together data points that are close to each other according to some similarity metric (e.g., Euclidean distance). K-means clustering groups together data points that are close to the mean of the cluster according to some similarity metric (e.g., Euclidean distance).

Both single-linkage and k-means clustering are guaranteed to converge to a local optimum (i.e., they will not get stuck in a suboptimal solution), but they may not necessarily converge to the global optimum (i.e., the best possible solution).

How the Hierarchical Clustering Algorithm Works

The hierarchical clustering algorithm works by grouping data points together in a tree-like structure. The algorithm starts by placing each data point in its own cluster. It then looks for two clusters that are closest to each other and combines them into a single cluster. This process is repeated until there is only one cluster left.

The hierarchical clustering algorithm can be used with any distance metric, but the most common metric is Euclidean distance. The algorithm can also be used with different linkage methods, but the most common method is single linkage.

Advantages and Disadvantages of Hierarchical Clustering

There are a few advantages and disadvantages of hierarchical clustering that you should take into account before implementing this algorithm in your own machine learning projects.

-Can be used with large datasets
-Does not require much computational power
-Results can be visualized easily
-Can be used with non-numeric data

-May produce suboptimal results compared to other clustering algorithms
-Results can be sensitive to the order of the data points

Leave a Reply

Your email address will not be published.