Course Study Note

Day 1 — Generative Models and Deep-Learning Foundations

I began with what it means to learn a data distribution, then reviewed tensors and neural-network foundations.

Date
2025-07-07
Course
2025 Generative Models Intensive — From VAE to Stable Diffusion
01Generative Model Overview

Study checkpoint for this day

02Deep-Learning Foundations

Study checkpoint for this day

03Dataset Visualization

Study checkpoint for this day

A day-level study path generated from the saved course topic order.

Topics from the day

  1. Generative Model Overview

    I compared generation with discrimination and connected likelihood to sampling.

  2. Deep-Learning Foundations

    I revisited tensor shapes

  3. Dataset Visualization

    I practiced inspecting distributions and outliers before choosing a model.

Flow from observed data through distribution learning to new samples
I treated a generative model as a distribution learner, not an image lookup table.

Generation versus discrimination

A classifier focuses on a conditional such as (p(y x)). A generative model works with (p(x)) or a joint distribution and samples a new (x). This view made the differences among autoregressive models, VAEs, GANs, and diffusion easier to compare.

Tensor shapes first

I printed batch, channel, height, and width before constructing the network. A loss can still return a number when normalization or flattening uses the wrong axis, so shape checks came before tuning.

Looking at the data

I inspected class balance, ranges, missing values, and duplicates before choosing a model. Preprocessing statistics belong to the training split; calculating them before the split leaks information.

Next question

The next step was to ask whether a difficult joint distribution could be rewritten as a sequence of conditional probabilities.

← Course home
Publication first-page preview