Harmonic Loss Trains Interpretable AI Models · HackerPapers discussions

Harmonic Loss Trains Interpretable AI Models — mentioned by yorwba

Sun, 16 Feb 2025 08:48:51 GMT

The author admits they "kinda stopped reading this paper" after noticing that they only used one hyperparameter configuration, which I agree is a flaw in the paper, but that's not an excuse for sloppy treatment of the rest of the paper. (It would however, be an excuse to ignore it entirely.) In particular, the assumption that |a_k| ≈ 0 initially is incorrect, since in the original paper https://arxiv.org/abs/2502.01628 the a_k are distances from one vector to multiple other vectors, and they're unlikely to be initialized in such a way that the distance is anywhere close to zero. So while the…

Paper and discussion history. A mention is not an endorsement.

Harmonic Loss Trains Interpretable AI Models — HN submission

Wed, 05 Feb 2025 20:36:29 GMT

Harmonic Loss Trains Interpretable AI Models

1 point; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.

Harmonic Loss Trains Interpretable AI Models — mentioned by westurner

Wed, 05 Feb 2025 01:04:20 GMT

"Harmonic Loss Trains Interpretable AI Models" (2025) https://arxiv.org/abs/2502.01628 Src: https://github.com/KindXiaoming/grow-crystals : > What is Harmonic Loss? Cross Entropy: https://en.wikipedia.org/wiki/Cross-entropy XAI: Explainable AI > Interpretability: https://en.wikipedia.org/wiki/Explainable_artificial_intelli... Right to explanation: https://en.wikipedia.org/wiki/Right_to_explanation

Paper and discussion history. A mention is not an endorsement.

Harmonic Loss Trains Interpretable AI Models — HN submission

Wed, 05 Feb 2025 00:15:59 GMT

Harmonic Loss Trains Interpretable AI Models

4 points; 2 discussion replies on HN. Paper and source history. A submission is not an endorsement.