PCA in Machine Learning. Why PCA is important. What PCA do.

PCA is one of the most popular Machine Learning technique in Data Science for Dimensionality reduction and for separate important features from noise data. As Wiki tells, PCA is mostly used as a tool in exploratory data analysis (EDA) and for making predictive models, in Python, R or other programming language. PCA is a statistical procedure that questions whether features representing the data are equally important. With this video I introduce my view on principal component analysis by highlighting following quick topics with simple examples: - what is PCA. - why rotation in PCA is useful? - How to understand variance and how it related with information? - What does information have to do with PCA? - Signal and noise in PCA. - Basic ideas and benefits of using PCA in real world projects. I did not touched math side on PCA, therefore I recommend to take a look for this to any Machine learning or Deep Learning book (recommending this one:    • The Best Machine Learning Book I have...  ). In this video I explain my personal opinion and views on PCA for dimensionality reduction. It can be differ from your. If you find I missed something important or want to fix me in any place, just let me know in the comments. See you on next my videos dedicated for Data Science! - Vytautas. #pca #datascience #machinelearningtips

• #science_technology
• #pca
• #principal_component_analysis
• #dimensionality_reduction
• #feature_reduction
• #machine_learning
• #data_science
• #deep_learning
• #ml_pca
• #machine_learning_pca
• #signal_and_noise
• #exploratory_data_analysis
• #eda
• #data_analysis
• #predictive_models
• #ml_book
• #data_noise
• #python_machine_learning
• #pca_python
• #pca_statistics