londogard
Re:Gzip and KNN Outperforms Transformers on Text Classification
on Thursday July 13, 2023 @09:19AM (#36708671)
Yes, what I'm saying is that gzip does not perform as well when it's not overlapping tokens exact.
Gzip does not support a "semantic" mode, hence it won't and does not (according to the papers metric) perform as well.
Deep learning can capture these semantic similarities.
Re:Gzip and KNN Outperforms Transformers on Text Classification
on Thursday July 13, 2023 @07:41AM (#36707677)
I'd like to note that this is only stronger on news.
Yahoo Questions it is not top performer. It's not far fetched to think that news are written in a similar way, sometimes even partly copied, and therefore have a lot of words in common. Yahoo Questions is a forum and I'd expect there to be a greater variation of word, but the word themself have a semantic similarity.
That is, gzip is strong when many words overlap (the size increase when gzipped is smaller) but if it's semantic similarity DNN's win everyday.
The results are interesting but not as interesting as it sounds IMO.
Re:Ask HN: Could you share your personal blog here?
on Tuesday July 04, 2023 @02:15PM (#36590546)
blog.londogard.com
Mainly Data Science or Kotlin I'm blogging about it at least for now.
Re:Log and track ML metrics, parameters, models with Git and DVC
on Tuesday May 23, 2023 @07:32AM (#36042820)
Thanks!
We solved 1. the same way, but it felt "off" somehow. Perhaps it's a good solution.
2. That's a sound solution, but a tiny bit cumbersome. I have projects where we deploy both classifier and regressor, where it'd nice to keep all in main. Alas, you can't have it all.
Re:Log and track ML metrics, parameters, models with Git and DVC
on Sunday May 21, 2023 @04:13AM (#36018897)
I really enjoy using DVC. I do have some drawbacks compared to other offering like MLFlow and W&B.
1. Harder to track experiments on remote VM's (e.g. Azure) as there's no server (we need to feed results back somehow) 2. Impossible (?) to track different types of experiments in the same repo. MLFlow has a way to define experiments and runs, which means I can easily group Regression vs Classification or even if I try a completely different task with the same data.
If anyone has a good suggestion on how to solve these two I'd love to fully commit to DVC!
Re:DuckDB 0.7.0
on Monday February 13, 2023 @05:33AM (#34772005)
The Polars integration is golden! Now I can use my two favorite tools without any awkward conversations via Arrow.
Really smooth, love it!
Re:TypeScript and Set Theory
on Friday April 22, 2022 @02:15AM (#31118771)
I think it's excalidraw
Re:Tribuo, a Machine Learning Library for Java
on Tuesday September 15, 2020 @04:10PM (#24486179)
Hi,
What would you say differentiates you from Smile which includes a simplistic datagrame, visualisation and support for CBLAS etc.
Is speed on par?
Re:AllenNLP Interpret: A Framework for Explaining Predictions of NLP M...
on Sunday September 29, 2019 @02:35AM (#21105493)
Awesome, I love to see how there's coming more and more frameworks for interpretability. It's incredibly important, especially when selling your solution to higher-ups.
There's another solution named LIME which seems to take a similar but more general approach, I like this more tailored idea as it'll probably give a better interpretation of the NLP questions.