32 citations · 41 across the 7 of their papers we have counts for
9 papers
Depth Laws for the Precision Floor of Trained Neural Networks: Amplification, Residual Scaling, and a Quantization-Aware Training Paradox
Ahmad S. Tarawneh
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 accur…
Synthetic minority data is redundant or invalid: a data-dependent validity theory and a de-biased test
Ahmad B. Hassanat, Ahmad S. Tarawneh, Ghada A. Altarawneh
For two decades, the standard remedy for class-imbalanced learning has been to fabricate synthetic minority examples, and the standard evidence of their validity has been a check t…
Stop Oversampling for Class Imbalance Learning: A Critical Review
Ahmad B. Hassanat, Ahmad S. Tarawneh, Ghada A. Altarawneh +1
For the last two decades, oversampling has been employed to overcome the challenge of learning from imbalanced datasets. Many approaches to solving this challenge have been offered…
Fuzzy Win-Win: A Novel Approach to Quantify Win-Win Using Fuzzy Logic
Ahmad B. Hassanat, Ghada A. Altarawneh, Ahmad S. Tarawneh +2
The classic win-win has a key flaw in that it cannot offer the parties the right amounts of winning because each party believes they are winners. In reality, one party may win more…
Deep learning for identification and face, gender, expression recognition under constraints
Ahmad B. Hassanat, Abeer Albustanji, Ahmad S. Tarawneh +6
Biometric recognition based on the full face is an extensive research area. However, using only partially visible faces, such as in the case of veiled-persons, is a challenging tas…
Deep Face Image Retrieval: a Comparative Study with Dictionary Learning
Ahmad S. Tarawneh, Ahmad B. A. Hassanat, Ceyhun Celik +3
Facial image retrieval is a challenging task since faces have many similar features (areas), which makes it difficult for the retrieval systems to distinguish faces of different pe…
Detailed Investigation of Deep Features with Sparse Representation and Dimensionality Reduction in CBIR: A Comparative Study
Ahmad S. Tarawneh, Ceyhun Celik, Ahmad B. Hassanat +1
Research on content-based image retrieval (CBIR) has been under development for decades, and numerous methods have been competing to extract the most discriminative features for im…
Pilot Comparative Study of Different Deep Features for Palmprint Identification in Low-Quality Images
A. S. Tarawneh, D. Chetverikov, A. B. Hassanat
Deep Convolutional Neural Networks (CNNs) are widespread, efficient tools of visual recognition. In this paper, we present a comparative study of three popular pre-trained CNN mode…
Victory Sign Biometric for Terrorists Identification
Ahmad B. A. Hassanat, Mahmoud B. Alhasanat, Mohammad Ali Abbadi +3
Covering the face and all body parts, sometimes the only evidence to identify a person is their hand geometry, and not the whole hand- only two fingers (the index and the middle fi…