This Streamlit app visually demonstrates how a neural network can approximate different nonlinear functions using various activation functions. It shows the power of neural networks and highlights why nonlinear activation is crucial in building complex models.

This project explores the structure of S&P 500 stock returns using Principal Component Analysis (PCA). The Streamlit app lets you interactively visualize how a few principal components capture most of the variance, see factor loadings, and get intuition for market-wide vs sector-specific movements in the index.