High-dimensional data can be challenging to work with because the number of variables can make it difficult to visualize, explore, and analyze the data. Additionally, high-dimensional datasets can be more susceptible to overfitting, where a model performs well on the training data but poorly on new data, due to the large number of variables. Techniques such as feature selection, dimensionality reduction, and regularization can help address these challenges. Meta-heuristic based feature selection is a technique used to select the most relevant features from a high-dimensional dataset. Meta-heuristics are optimization algorithms that are designed to find near-optimal solutions to complex problems. Meta-heuristic based feature selection has several advantages. It can handle high-dimensional datasets and can effectively select the most relevant features while reducing overfitting. Additionally, meta-heuristic algorithms are flexible and can be easily adapted to different types of models and fitness functions. Here we will discuss how to extract the optimal set of features from meta-heuristic based feature selection approaches in high dimensional datasets. Speaker(s): Dr. Pradip Dhal, Virtual: https://events.vtools.ieee.org/m/363094