IEEE Transactions

By O. Yadid-Pecht, D. Wilson, M. Zaghloul. 2020

The recent years have seen an explosive growth of research applied to sensory systems in the areas of life sciences, physical sciences and engineering. Such activities require inter-disciplinary collaboration between scientists, engineers, and practitioners to solve complex real world problems. The emerging CASS activities in Sensory Systems should create innovative solutions for today's problems and pose new challenges for the CASS community to build new bridges at the frontiers of Systems Engineering. From an engineering perspective sensory circuits and systems are demanding with extreme power limitations, requiring robustness and reliability in different operation environments. In applications like implants, integration of sensors and transducers for both power and signaling is required. In many ways, sensory circuits and systems are challenging the state-of-the-art circuit design, and cross-field collaboration is important for utilizing existing technologies. It is hoped that new and strong research should emerge form these efforts and make way technology progress. Topics of this special issue are intended to cover a broad spectrum involving Smart Sensors and Sensory Systems. These include, but are not limited to: • Image Sensors • MEMS • Acoustic Sensors • Chemical Sensors • Vision Systems • Chemical Sensors • Sensor devices and interface circuits • Sensory models • Networked Sensors • Olfactory Sensors • Neuromorphic Circuits

Subfields: Statistics and Probability

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Statistics and Probability

Citations in the corpus

Visualisation and 'diagnostic classifiers' reveal how recurrent and recursive neural networks process hierarchical structure (2017, neutral): “As we argue in the full paper, neither theoretical results [Siegelmann and Sontag, 1995], nor handcrafted examples [Gers and Schmidhuber, 2001; Rodriguez, 2001], nor large-scale NLP applications [Sutskever et al.”
Visualisation and 'Diagnostic Classifiers' Reveal how Recurrent and Recursive Neural Networks Process Hierarchical Structure (Extended Abstract) (2018, unknown): “As we argue in the full paper, neither theoretical results [Siegelmann and Sontag, 1995], nor handcrafted examples [Gers and Schmidhuber, 2001; Rodriguez, 2001], nor large-scale NLP applications [Sutskever et al.”
Classical Planning in Deep Latent Space: Bridging the Subsymbolic-Symbolic Boundary (2017, methodology): “However, they allow us to implement a successor function which can be used in any symbolic, forward state space search algorithm such as A∗ [Hart et al., 1968].”