Peter Sussner

Universidade Estadual de Campinas (UNICAMP)

Papers

Total Citations

H-Index

About

Peter Sussner is a leading figure in computational intelligence, whose research bridges fuzzy systems, mathematical morphology, and neural networks. His most significant contributions lie in the theory and application of fuzzy associative memories (FAMs) and morphological neural networks (MNNs). Sussner introduced the Kosko Subsethood Fuzzy Associative Memory (KS-FAM), a model grounded in subsethood theory that has proven effective for pattern recognition in computer vision, earning over 26 citations. He also pioneered the use of heteroassociative MNNs for vision-based self-localization in mobile robotics, a landmark work with 25 citations that demonstrated how morphological operations can replace traditional neural computations for robust spatial reasoning. Expanding the theoretical foundations of the field, Sussner developed Θ-Fuzzy Associative Memories (Θ-FAMs), which generalize single-layer FAM architectures to handle more complex, rule-based inference with enhanced storage capacity. His work is characterized by a rigorous mathematical approach that unifies fuzzy logic with morphological image processing, producing models that are both theoretically sound and practically deployable. With over 20 citations on his Θ-FAM framework alone, Sussner’s research continues to influence advances in autonomous navigation, computer vision, and hybrid intelligent systems.