* Neural Networks: Composed of layers of nodes (neurons), where each node processes input and passes the result to the next layer.
* Layers:
* Input layer: Takes in raw data (e.g., pixels of an image).
* Hidden layers: Perform transformations and computations on inputs.
* Output layer: Produces the prediction or result (e.g., a label).
* Forward Propagation: Data moves from input to output layer through weights and activation functions.
* Backpropagation: The model learns by adjusting weights using gradients from loss function optimization (e.g., via Stochastic Gradient Descent).
