Polynomial ADALINE for Time Series Forecasting

This project implements an ADALINE (Adaptive Linear Neuron) neural network using PyTorch to forecast a time series based on the Logistic Map dynamics. It includes a custom data manager to generate polynomial and cross-term features, an ADALINE model trained using the Delta Rule (pattern-by-pattern), and an experiment runner that evaluates the model's performance and robustness across different learning rates, both with clean and noisy data.