HackerTrans
TopNewTrendsCommentsPastAskShowJobs

karxxm

no profile record

Submissions

Is Odd AI

github.com
1 points·by karxxm·2 years ago·1 comments

comments

karxxm
·last year·discuss
Replacing juniors with AI is stupid because who will be the next senior? AI won't learn anything while performing inference only.
karxxm
·2 years ago·discuss
A wonderful satire!
karxxm
·2 years ago·discuss
Most volume renderers lack a good transfer function editor. When analyzing volumes, especially explorative analysis, the most effective tool is to dial in colors and opacities for certain value ranges, in order to find structures.

The volume rendering engine I have been working on uses a histogram for the value distribution, and on top of it, one can draw lines that indicate the opacity. Additionally, one can set colors to the control points, which are then linearly interpolated for the given ranges.
karxxm
·2 years ago·discuss
What’s that color-map called?
karxxm
·3 years ago·discuss
Most “professional” techno djs in Germany use Traktor, if they are not using Ableton or the CDJs
karxxm
·3 years ago·discuss
It depends I guess.

If you solve a problem that had been around for a while and LLMs offer a new way of approaching it, then it can definitely become a paper.

Of cause one has to verify in sophisticated experiments, that this approach is stable.
karxxm
·3 years ago·discuss
Unfortunately no mention of colorbrewer (https://colorbrewer2.org)
karxxm
·3 years ago·discuss
Not true. You need a distance matrix (for classical PCA it's a covariance matrix), which scales quadratically with the number of points you want to compare. If you have 1 Mio. vectors, each creating a float entry in the matrix, you will end up with approx (10^6)^2 / 2 unique values, which is roughly 2000Gb of memory.
karxxm
·3 years ago·discuss
Unfortunately this is not feasible with a large amount of words due to the quadratic scaling. But thanks for the response!
karxxm
·3 years ago·discuss
You wrote „out of the box“, did you find a way to improve this?
karxxm
·3 years ago·discuss
Some architectures are relatively well understood. Eg in CNNs, the first layers detect low level features like edges, gradients, etc. The next layer then combines these features to more complex structures like corners or circles. Next layer will combine these features to even higher level features and so on. [1]

Typically, you can take a pre-trained model and retrain it on your new dataset by only changing the weights of the last layer(s).

Some loss functions even measures the difference between the high-level features of two images, typically extracted from a pre-trained CNN (Perceptual Loss).

[1]Matt Zeiler did an amazing work on these findings 10 years ago (https://arxiv.org/abs/1311.2901).
karxxm
·3 years ago·discuss
I have not seen many work on explainable AI regarding large language models. I remember many very nice visualizations and visual analysis tools trying to comprehend, what the network „is seeing“ (eg. in the realm of image classification) or doing