nikgeo25

joined 10 months ago
sorted by: new top controversial old
ML for time series regression [P] in c/machinelearning@academy.garden
[–] nikgeo25@alien.top 1 points 10 months ago

anything that implements ARIMA

[D] how do you remember methods in papers you read? in c/machinelearning@academy.garden
[–] nikgeo25@alien.top 1 points 10 months ago

There are lots of engineering tricks given fancy names in ML. No point in memorizing all of them, but keep reading them to maintain intuition.

[D] Why are ML model outputs not tested regarding statistical significance? in c/machinelearning@academy.garden
[–] nikgeo25@alien.top 1 points 10 months ago

Probably because most aren't statistically significant...

[D] How to train a model that'll generate an "average" image based on a large set of images? in c/machinelearning@academy.garden
[–] nikgeo25@alien.top 1 points 10 months ago (1 children)

If the model has the following format:

Encoder, diffusion in latent space, decoder

you can average the embedding right before the decoder. Just make sure your averaging is of a representation that can be meaningfully averaged. E.g. averaging images would result in garbage, but their corresponding embeddings might provide something useful.

[P] Searching for "smart" networks built from NAND gates and memory using GA in c/machinelearning@academy.garden
[–] nikgeo25@alien.top 1 points 10 months ago (1 children)

No way that's exactly what I've been doing as a side project.