This is part three of the Principal Components in TypeScript series, and it focuses on the application of PCA to a visual explanation of vision neural networks. Principal Components in TypeScript Previous parts: Part 1: https://hackernoon.com/principal-components-in-typescript-part-1 Part 2: https://hackernoon.com/principal-components-in-typescript-part-2-how-pca-actually-works-under-the-hood Part 1: https://hackernoon.com/principal-components-in-typescript-part-1 https://hackernoon.com/principal-components-in-typescript-part-1 Part 2: https://hackernoon.com/principal-components-in-typescript-part-2-how-pca-actually-works-under-the-hood https://hackernoon.com/principal-components-in-typescript-part-2-how-pca-actually-works-under-the-hood If you need a TL;DR, just go through the code or grab the package here on npm If you need a TL;DR, just go through the code or grab the package here on npm here on npm Not a Code Blog This is not a code blog. There’s no easy copy-paste solution here. If that’s what you want, go straight to the source code above. Now this post attempts to use PCA in a totally different direction compared to the vanilla dimensionality reduction or to data compression discussed in the earlier posts. Basically, for this post, I'm going to walk you through how to attempt to uncover insights from CNN features. But before that, we must answer a very important question. Are CNNs outdated? Is this the age of Transformers? Are CNNs outdated? Is this the age of Transformers? Not exactly, as ConvNext proved in 2022, CNNs still have a role to play in most vision tasks, as well as being pretty much the only option for highly performant edge deployment on extremely compute-limited devices. ConvNext Since we have now answered the above question unconvincingly, let us attempt to figure out how to do it. A note of warning, while I have specified Typescript here (since that is what my library is written in), we still do not have a convincing CNN solution in pure JS or Typescript. The good news, I am working on one, and even though it isn't close to release, I am going to leave the link to my