About But what is a neural network?

Diffusion Models: Score-Based Image Generation via Reversed Noise Processes Gradient Descent Minimizing Neural Network Cost Function via Backpropagation Large Language Models Predict Next Words Using Transformer Attention Mechanisms Self Attention Mechanism in Transformers LLMs Store Facts in Multi-Layer Perceptrons Inside Transformer Networks Backpropagation: Computing Gradients via the Chain Rule Transformer Architecture: Attention, Embeddings, and Feed-Forward Blocks