Dimension Reduction

For basic Understanding of Dimensionality Reduction please go through this article first: Dimensionality Reduction Why t-SNE? : PCA retains the overall global variance of dataset. but it will not be able to capture the local variance of dataset. t-SNE helps in capturing local variance of dataset. t-SNE is non linear…

Large number of dimension confuse the models. and we need to extract the relevant features to feed models. Features Types Relevant features Irrelevant features : keys like this: that, is ,there (stop words) Redundant features: features which are irrelevant in present of others Why Dimensionality reduction Perfomance adding only relevant features avoid the overfitting. With…

Scientists develop AI model that can accurately and efficiently determine human activities from video footage Scientists have developed an innovative approach for automatic human activity recognition — a computer vision tool that allows a system to classify a person’s action or state using video footage. The proposed solution is based…

T-SNE: t-Stochastic neighborhood embedding It is mostly used for data visualization. T-sne preserves the local structure. which means the distances between the points at the local surroundings. PCA preserves the Global structure of the data while transforming from higher dimensions to the dimensions. …

Explanation and derivation of PCA from a geometric point of view “ Dimensionality reduction refers to techniques for reducing the number of input variables in training data.’’ Among the number of techniques available, we will thoroughly look into PCA (Principal Component Analysis). Table of Contents: PCA intuition (geometric) Column standardization Optimization problem Calculation…

Problem Statement You are working in a software company and they want you to classify the 500 emojis as per their type. all smile together, all angry together, etc. (Note: all emojis are 100*100 sizes). How you will do it? As per the question, it looks like a classification problem so we…

In Part 1 we went over how to encode categorical features that are either nominal or ordinal. Completing this process gave us a DataFrame with more than double our original 82 features. …