Results 111 to 120 of about 52,085 (312)

A Space-Variant Visual Pathway Model for Data Efficient Deep Learning

Frontiers in Cellular Neuroscience, 2019
We present an investigation into adopting a model of the retino-cortical mapping, found in biological visual systems, to improve the efficiency of image analysis using Deep Convolutional Neural Nets (DCNNs) in the context of robot vision and egocentric ...
Piotr Ozimek, Nina Hristozova, Lorinc Balog, Jan Paul Siebert   +3 more
doaj   +1 more source

Transistor‐Level Activation Functions via Two‐Gate Designs: From Analog Sigmoid and Gaussian Control to Real‐Time Hardware Demonstrations

Advanced Materials, EarlyView.
Screen gate‐based transistors are presented, enabling tunable analog sigmoid and Gaussian activations. The SA‐transistor improves MRI classification accuracy, while the GA‐transistor supports precise Gaussian kernel tuning for forecasting. Both functions are implemented in a single device, offering compact, energy‐efficient analog AI processing ...
Junhyung Cho, Youngmin Han, Won Woo Lee, Youngwoo Yoo, Kannan Udaya Mohanan, Chang‐Hyun Kim, Junhwan Choi, Young‐Joon Kim, Wonjun Shin, Hocheon Yoo   +9 more
wiley   +1 more source

Soft and Strong: Elastic Conductors with Bio‐Inspired Self‐Protection

Advanced Materials, EarlyView.
A general reverse‐engineering approach is demonstrated for designing functional yarns that uses woven fabric architecture as a structural framework. The fabric‐based stretchable conductive yarns combine flexibility, high elasticity, low stiffness, self‐protection, and weavability with conventional textile processes. By fine‐tuning the number of elastic
Chenglong Zhang, Xiulun Yin, Chris Zhou, Xin Lu, Siying Wu, Ying Li, Addie Bahi, Sukhneet Kaur Dhillon, Orlando J. Rojas, Jinhua Jiang, Nanliang Chen, Frank K. Ko, John D. W. Madden   +12 more
wiley   +1 more source

GAMNet: Global attention via multi‐scale context for depth estimation algorithm and application

IET Image Processing
Deep neural networks significantly enhance the accuracy of the stereo‐based disparity estimation. Some current methods suffer from inefficient use of the global context information, which will lead to the loss of structural details in ill‐posed areas. To
Huitong Yang, Liang Lei, Haiwei Sang
doaj   +1 more source

Video Anomaly Detection Using Pre-Trained Deep Convolutional Neural Nets and Context Mining [PDF]

, 2020
Chongke Wu, Sicong Shao, Cihan Tunc, Salim Hariri   +3 more
openalex   +1 more source

Progressive Neural Networks

, 2016
Learning to solve complex sequences of tasks--while both leveraging transfer and avoiding catastrophic forgetting--remains a key obstacle to achieving human-level intelligence. The progressive networks approach represents a step forward in this direction:
Desjardins, Guillaume, Hadsell, Raia, Kavukcuoglu, Koray, Kirkpatrick, James, Pascanu, Razvan, Rabinowitz, Neil C., Rusu, Andrei A., Soyer, Hubert   +7 more
core  

Halide Perovskite–Chalcohalide Nanocrystal Heterostructures as a Platform for the Synthesis and Investigation of the CsPbCl3–CsPbI3 Epitaxial Interface

Advanced Materials, EarlyView.
In this work, perovskite–chalcohalide CsPbCl3–Pb4S3Cl2 heterostructures are exploited to study the Cl→I exchange reaction and to isolate new types of intermediate structures, in particular emissive CsPbI3–CsPbCl3–Pb4S3Cl2 heterostructures, with partial I‐alloying of the CsPbCl3 domain and at the perovskite–chalcohalide interface, having a 5.6% lattice ...
Nikolaos Livakas, Irina Skvortsova, Juliette Zito, Yurii P. Ivanov, Aswin Asaithambi, Andrea Toma, Annick De Backer, Muhammad Imran, Sandra Van Aert, Giorgio Divitini, Ivan Infante, Sara Bals, Liberato Manna   +12 more
wiley   +1 more source

Artificial Quantum Neural Network: quantum neurons, logical elements and tests of convolutional nets [PDF]

, 2018
V. I. Dorozhinsky, Oleg Pavlovsky
openalex   +1 more source

Organic Electrochemical Transistors for Neuromorphic Devices and Applications

Advanced Materials, EarlyView.
Organic electrochemical transistors are emerging as promising platforms for neuromorphic devices that emulate neuronal and synaptic activities and can seamlessly integrate with biological systems. This review focuses on resultant organic artificial neurons, synapses, and integrated devices, with an emphasis on their ability to perform neuromorphic ...
Kexin Xiang, Jiajun Song, Hong Liu, Junxin Chen, Feng Yan   +4 more
wiley   +1 more source

Ferroelectrics Hybrids: Harnessing Multifunctionality of 2D Semiconductors in the Post‐Moore Era

Advanced Materials, EarlyView.
In this Review, the state of art of ferroelectric hybrid systems—combining ferroelectrics, 2D semiconductors, and molecular switches is presented—as next‐generation platforms for high‐density, multifunctional electronics. By discussing 2D FeFET applications, nanoscale material downscaling, M3D integration, and emerging ferroelectrics, it highlights ...
Haixin Qiu, Xiaoshi Qian, Dahong Qian, Paolo Samorì   +3 more
wiley   +1 more source