Abdulmajeed Alameer

Papers

Total Citations

H-Index

About

Abdulmajeed Alameer’s research lies at the intersection of computational neuroscience, computer vision, and machine learning, with a focus on bridging the gap between biological and artificial visual systems. His most cited work, “An elastic net-regularized HMAX model of visual processing” (2015), introduces a novel regularization technique to the hierarchical MAX (HMAX) model—a biologically inspired framework for object recognition. By applying elastic net regularization, Alameer enhances the model’s ability to learn sparse, discriminative features, improving its performance in categorizing objects under challenging conditions. This contribution addresses a critical limitation in robotic vision, where systems often fail to match human-level perception. With 5 citations, the paper has influenced subsequent efforts to refine bio-inspired vision algorithms for autonomous systems. Alameer’s work underscores his commitment to developing more robust, interpretable models that emulate the human visual hierarchy, offering a pathway toward smarter robotics and AI. His research is particularly valuable for students and researchers exploring how computational models can integrate biological principles to achieve greater efficiency and accuracy in real-world visual tasks.