One of the most popular dimensionality reduction method is Principal Component Analysis (PCA), which reduces the dimension of the feature space by finding some linear combinations of the original variables that have maximal standard deviation. PCA can reduce the dimension of the data dramatically and without losing too much information when the linear correlations of the data are strong. (And in fact you can also measure the actual extent of the information loss and adjust accordingly.)

Another popular method is t-Stochastic Neighbor Embedding (t-SNE), which does non-linear dimensionality reduction. It is typically used for data visualization, but can also be used for reducing the feature space and clustering, to mention just a few.

Contrary to PCA it is not a linear algebra technique but a probablistic one. The original paper describes the working of t-SNE as:

“t-Distributed stochastic neighbor embedding (t-SNE) minimizes the divergence between two distributions: a distribution that measures pairwise similarities of the input objects and a distribution that measures pairwise similarities of the corresponding low-dimensional points in the embedding”.

For example, it was used for dimensionality reduction of the database of handwritten digits. The data set contains thousands of images of digits from 0 to 9, which researchers used to test their clustering and classification algorithms. Each row of the data set is a version of the original image (size 28 x 28 = 784) and a label for each image (zero, one, two, three, …, nine).The dimensionality was reduced from 784 (pixels) to 2 (dimensions in visualization). Projecting to two dimensions allows to visualize the high-dimensional original data set.

See for example,

https://towardsdatascience.com/visualising-high-dimensional-datasets-using-pca-and-t-sne-in-python-8ef87e7915b

Read this article:

https://medium.com/analytics-vidhya/pca-vs-lda-vs-t-sne-lets-understand-the-difference-between-them-22fa6b9be9d0

This may help https://reneshbedre.com/blog/tsne.html

Thanks Dr Santhosh Kumar

Thanks dear Renesh Bedre