This repository implements a Physics-Informed Neural Network (PINN) to solve the 1D Diffusion Equation using PyTorch. PINNs use deep learning to approximate solutions to partial differential equations (PDEs), enforcing both boundary conditions and the governing equation during training.

This code:

• Solves the 1D Diffusion Equation using a physics-informed neural network.
• Implements automatic differentiation to compute PDE residuals.
• Uses boundary and initial conditions for supervised learning.
• Supports Adam and L-BFGS optimizers for training.
• Provides visualizations of the learned solution against the exact solution.

This project is licensed under the MIT License. See LICENSE for details.