PresentDelivery4277

joined 1 year ago
sorted by: new top controversial old
I’m having a hard time understanding the potential of Machine Learning [D] in c/machinelearning@academy.garden
[–] PresentDelivery4277@alien.top 1 points 11 months ago

There will always be a need for specialized knowledge. Maybe take an introduction course to get an idea of whether you enjoy ML or not. You'll at least get an overview, which is always useful to have, even if you don't end up in the field. In the end the important thing is that if you end up specializing, that you enjoy it. There are plenty of other things to get into in CS if ML isn't your thing.

[D] Without a clear leader in AI do you think the race to AGI will start to get chaotic? in c/machinelearning@academy.garden
[–] PresentDelivery4277@alien.top 1 points 11 months ago

Shouldn't we be seriously considering not attempting AGI? Other than the general philosophical and ethical considerations, achieving AGI is a near surefire way to ensure that most of us are out of a job.

1
Looking for a very small text classification transformer (alien.top)
 

I'm looking for suggestions for a transformer model that I can fine-tune for a text classification task. Due to hardware constraints the model has to be fairly small. Something in the order of a 50 MB weight file.

1
Looking for a very small text classification transformer [R] (alien.top)
 

I'm looking for suggestions for a transformer model that I can fine-tune for a text classification task. Due to hardware constraints the model has to be fairly small. Something in the order of a 50 MB weight file.

I have an idea but don't know where to start or apply what I know [P] in c/machinelearning@academy.garden
[–] PresentDelivery4277@alien.top 1 points 1 year ago

Welcome to MIR (music information retrieval). If this was easy, I would have been done with my masters 2 years ago. What you are describing, multiple instrument transcription, is still an open research question and if you can satisfactorily solve it you will make a lot of very select researchers very happy. If you want to limit this to just a guitar you could probably start with an existing transcription algorithm and teach something to derive fingering. Something like a HMM would probably work fine.