Author

Ahmad S. Tarawneh

h-index 17 View on Semantic Scholar

We have 3 of 63 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

#machine learning Preprint Sep 2026

Depth Laws for the Precision Floor of Trained Neural Networks: Amplification, Residual Scaling, and a Quantization-Aware Training Paradox

How many bits does a network need before its accuracy collapses, and how does this grow with depth? We study the precision floor, the perturbation level or bit-width at which accuracy falls halfway to chance, in MLPs, CNNs, Vision Transformers and nine pretrained language models, under post-training quantization (PTQ)...

Ahmad S. Tarawneh · 0 citations

Open access Jul 2026

A Sign-Symmetric Reformulation of the Hassanat Distance for Data with Negative Feature Values

The Sign-Symmetric Hassanat Distance (SHasD), a single branch-free formula D(a,b)=|a−b|/(1+max(|a|,|b|)) that is invariant under the reflection x↦−x, coincides exactly with HasD on non-negative data, and removes the conditional shift entirely.

Mohammad Saad Alaydaa, Gaseb N. Alotibi, Ahmad S. Tarawneh et al. · Symmetry · 0 citations

Open access Jul 2026

On the Optimality of k=n in k-Nearest Neighbor Classification: Sub-Optimality Rates, Dimension-Aware Selection, and Hassanat Distance Comparison

The theoretical results provide a principled non-cross-validated alternative to the classical n rule, and cross-validation remains the strongest k-selection strategy when computationally feasible.

Ahmad Hassanat, A. A. Alkasasbeh, Esra’a Alkafaween et al. · Mathematics · 1 citation