kraegar

joined 2 years ago
sorted by: new top controversial old
What tools do you use? in c/datascience@lemmy.world
[–] kraegar@lemmy.world 1 points 1 year ago

I know it's an old thread, but I want there to be more DS stuff in the Lemmy.

Python is arguably the defacto standard. Jupyter gets used a lot (but shouldn't be used to frequently IMO).

I haven't used R but it seems to be a distant second to Python. That being said, it really depends on the industry!

Generally my setup is VSCode and Anaconda developing on remote VMs.

You've been instantly teleported two feet to the left. How does this affect you? in c/asklemmy@lemmy.ml
[–] kraegar@lemmy.world 6 points 2 years ago

my spinal cord has been severed and I feel hot prickles on my cheeks...

I read that as hot pickles and got realllllllly confused until I reread it.

PSA: Mastodon is NOT Twitter and does not aim to be. in c/fediverse@lemmy.world
[–] kraegar@lemmy.world 0 points 2 years ago (1 children)

George Takei feels like half the reason I still even used twitter.

A lot of the communities I interacted with because people shilling their products, but George remained.

Swapping to Mastodon was something I had low expectations for, but it turned out great.

2
Reversible Instance Normalization for Accurate Time-Series Forecasting against Distribution Shift (openreview.net)
 

I found this paper when implementing TSMixer in darts and thought it was worth sharing.

As far as I know, it may not be relevant to non-timeseries problems. That being said, does anybody know of instance normalization outside of timeseries? It is obviously similar to batch normalization but is slightly different.

I added RIN to an N-HiTS model using the Energy benchmark dataset and got 21% and 22% reduction in MSE and MAE, respectively. This required two lines of code to be added to the model definition and increased compute time in no noticeable manner.