EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Interpreting How Neural Networks Infer Scatterer Geometry from Echolocation Echoes

Ganesh U. Patil, Hyung‐Suk Kwon, Bogdan‐Ioan Popa

Advanced Intelligent Systems · 2026-08 · 8 (8)

DOI: 10.1002/aisy.70434 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Advanced Intelligent Systems, online erschienen am 24.05.2026. Verfasst von Ganesh U. Patil und 2 weiteren Autor:innen. Die Arbeit nennt 39 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: U.S. Office of Naval Research.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Artificial echolocation seeks to emulate biosonar for inferring shape (scatterer geometry) from acoustic echoes. Many promising approaches use convolutional neural networks (CNNs), but how these networks make decisions remains unclear, leaving model development largely empirical. This work introduces an interpretability framework for a robotic perception system composed of collections of specialized CNNs (SCNNs), each trained to recognize a specific shape. By leveraging the shallow SCNN architecture, convolutional features are mapped to decision neurons, and a feature‐importance metric is defined to reveal the echo cues that drive classifications. The analysis shows that SCNNs rely on the relative emphasis of several cues and that perturbing these cues predictably alters model outputs. In addition, decreasing signal‐to‐noise ratio in measured echoes is shown to obscure these cues, explaining the limits of generalization from synthetic to measured data. The framework transforms an opaque classifier into a transparent one, offering new insight into how neural networks parse echolocation echoes and providing guidance for the design of more interpretable and robust robotic perception systems.

Förderung

  • U.S. Office of Naval Research

Zitieren

APA

Patil, G. U., Kwon, H., & Popa, B. (2026). Interpreting How Neural Networks Infer Scatterer Geometry from Echolocation Echoes. Advanced Intelligent Systems, 8(8). https://doi.org/10.1002/aisy.70434

Vancouver

Patil GU, Kwon H, Popa B. Interpreting How Neural Networks Infer Scatterer Geometry from Echolocation Echoes. Advanced Intelligent Systems. 2026;8(8). doi:10.1002/aisy.70434

BibTeX
@article{Patil2026,
  author = {Patil, Ganesh U. and Kwon, Hyung‐Suk and Popa, Bogdan‐Ioan},
  title = {Interpreting How Neural Networks Infer Scatterer Geometry from Echolocation Echoes},
  journal = {Advanced Intelligent Systems},
  year = {2026},
  volume = {8},
  number = {8},
  doi = {10.1002/aisy.70434}
}
Kostenlos starten →