I don't really care that they all look alike as long as the sites usable to me for its intended purposes. Honestly, having each site have its own brand is annoying to me.
For years of dealing with badly designed sites, I wished then that they _copy_ a better design even if it looked generic. Even copying a simple but usable design would have made many sites easier to use.
I don't want the site to win an art contest, I want the information to make a decision. At a min just be easy in the eyes and intuitive to use and get the info.
An adjacent question: is there an input dataset you can use for training that be computed in closed form so that when you train on your target dataset, learning is effecient.
Methods like formula driven supervised learning exist to arrive a good pretrained weight state, but could this procedure be generalized for specific datasets or flavors of input data.
I met Pete when I worked at kitware. Would u have time for a fifteen min call? I'm interested in the position but have questions about viabikity given that capabilitiea of ai. Send an email.
Why is this not a typical data augmentation method for training deep networks? It would allow the networks to learn invariants that's align with humans. Currently, I suppose none of these dithered images would be correctly classified.
Perhaps because inference on dithered images is pretty rare, not a common or popular thing to do? Otherwise, people would train on dithered images. NNs are trained on noisy images. Training with dither would not learn any other invariants besides how to see through dither, it doesn’t automatically generalize to anything else.
Which NNs and what tasks are you thinking of? DLSS, for example, reconstructs texture, along with other denoisers, as well as all video models. Are you thinking only of object recognition?
Why do you believe training on dithered images would learn how to see through any other kinds of image modification? In my experience, image NNs learn only what you explicitly show them, and they don’t learn concepts they’re not trained on. All the denoisers I’ve ever seen have trouble handling subtle changes in pixel filtering they haven’t seen in the training data, and they don’t easily learn how to denoise things like clouds or reflections. I’d be willing to bet that if you trained on halftoned images, NNs would not be able to handle Floyd Steinberg dither. They just don’t generalize automatically.
> This image is a halftone/thermal print styled photograph. The photo features a group of four people posing closely together indoors or in front of a windowed backdrop:
There are many features in an image dataset which a can correctly classify the dataset. Neural nets usually focus in texture which we human clearly don't, we focus on a higher level abstraction and usually ignore texture. Using either would encourage the network to use broader features and ignore texture
The authors experience is not mine. I have an app/website combo deployed that is getting 60+ visitors a day and the app is getting downloaded weekly. Both are growing. All "vibe" coded.
Now I have 20 YOE in software too before the booon of AI.
