Results 241 to 250 of about 60,411 (286)

Dual‐Mode Oscillations in SiOx‐Based Threshold Switching Devices for Unconventional Probabilistic Computing

Advanced Intelligent Discovery, EarlyView.
To enable versatile unconventional computing, a single SiOx threshold switching device is engineered to exhibit controllable dual‐mode oscillation. By modulating the input voltage, the device selectively provides stable full oscillation for oscillatory neural networks and stochastic probabilistic oscillation for probabilistic bits and true random ...
Hyeonsik Choi, Jihyun Kim, Yonghun Kim, Jiyong Woo   +3 more
wiley   +1 more source

Balancing accuracy and efficiency: co-design of hybrid quantization and unified computing architecture for spiking neural networks. [PDF]

Front Neurosci
Li J, Xu M, Dong H, Lan B, Liu Y, Chen H, Zhuang Y, Xie Y, Chen L.   +8 more
europepmc   +1 more source

Clinically Informed Intelligent Classification of Ovarian Cancer Cells by Label‐Free Holographic Imaging Flow Cytometry

Advanced Intelligent Systems, Volume 7, Issue 3, March 2025.
Quantitative phase maps of single cells recorded in flow cytometry modality feed a hierarchical architecture of machine learning models for the label‐free identification of subtypes of ovarian cancer. The employment of a priori clinical information improves the classification performance, thus emulating the clinical application of liquid biopsy during ...
Daniele Pirone, Beatrice Cavina, Daniele Gaetano Sirico, Martina Mugnano, Vittorio Bianco, Lisa Miccio, Anna Myriam Perrone, Anna Maria Porcelli, Giuseppe Gasparre, Ivana Kurelac, Pasquale Memmolo, Pietro Ferraro   +11 more
wiley   +1 more source

Learning-efficient spiking neural networks with multi-compartment spatio-temporal backpropagation. [PDF]

iScience
Liu Y, Wang Y, Zhang C, Yu L, Fang Y, Chen F.   +5 more
europepmc   +1 more source

Haptic In‐Sensor Computing Device Based on CNT/PDMS Nanocomposite Physical Reservoir

Advanced Intelligent Systems, Volume 7, Issue 3, March 2025.
Using a porous carbon nanotube‐polydimethylsiloxane nanocomposite, a sensor array integrated with a physical reservoir computing paradigm capable of in‐sensor computing is demonstrated. The device is able to classify between nine objects with an accuracy above 80%, opening the possibility for low‐power sensing/computing for future robotics.
Kouki Kimizuka, Saman Azhari, Shoshi Tokuno, Ahmet Karacali, Yuki Usami, Shuhei Ikemoto, Hakaru Tamukoh, Hirofumi Tanaka   +7 more
wiley   +1 more source

Unveiling the role of local metabolic constraints on the structure and activity of spiking neural networks. [PDF]

PLoS Comput Biol
Jaras I, Orchard ME, Maldonado PE, Vergara RC.   +3 more
europepmc   +1 more source

Seeing Through the Face: Robust Facial Diagnosis Enhanced by Landmark Detection and Pose Normalization

Advanced Intelligent Systems, EarlyView.
This study proposes a robust, generalizable new approach for facial type diagnosis. Based on landmark detection and pose normalization, a 94.7% diagnostic accuracy is achieved by Combined Heatmap Regression and Coordinate Regression network. This research makes the AI‐generated preliminary diagnosis more interpretable and reducing the impact of ...
Qianyang Xie, Zixian Jiao, Guo Bai, Huimin Zhu, Dahe Zhang, Hui Li, Haixia Lu, Xin Nie, Qing Li, Duohong Zou, Zhiguo Yin, Peilun Li, Chi Yang   +12 more
wiley   +1 more source

Temporal Hierarchy in Spiking Neural Networks

Moro F, Aceituno PV, Kriener L, Payvand M.   +3 more
europepmc   +1 more source

Reinforced liquid state machines-new training strategies for spiking neural networks based on reinforcements. [PDF]

Front Comput Neurosci
Krenzer D, Bogdan M.
europepmc   +1 more source

Dynamic spatio-temporal pruning for efficient spiking neural networks. [PDF]

Front Neurosci
Gou S, Fu J, Sha Y, Cao Z, Guo Z, Eshraghian JK, Li R, Jiao L.   +7 more
europepmc   +1 more source