Having established the mathematical framework for the forward and reverse diffusion processes, we now address how to implement the reverse (denoising) step. This requires a trainable model that can learn to estimate the noise added at a specific timestep t, given the noisy data xt.
This chapter concentrates on the architecture and training procedure for this core model. We will cover:
Upon completing this chapter, you will understand the design principles of the neural network used within diffusion models and the procedure for training it to perform the denoising task.
4.1 The U-Net Architecture for Noise Prediction
4.2 Integrating Timestep Information
4.3 Defining the Training Objective
4.4 Simplified Training Loss Derivation
4.5 The Training Algorithm
4.6 Hands-on Practical: Setting up the U-Net
© 2025 ApX Machine Learning