Results 91 to 100 of about 22,800 (222)

A multi-stage neural network approach for coronary 3D reconstruction from uncalibrated X-ray angiography images

Scientific Reports, 2023
We present a multi-stage neural network approach for 3D reconstruction of coronary artery trees from uncalibrated 2D X-ray angiography images. This method uses several binarized images from different angles to reconstruct a 3D coronary tree without any ...
Kritika Iyer, Brahmajee K. Nallamothu, C. Alberto Figueroa, Raj R. Nadakuditi   +3 more
doaj   +1 more source

Harnessing Phase Dynamics Across Diverse Frequencies with Multifrequency Oscillatory Neural Networks

Advanced Intelligent Discovery, EarlyView.
Oscillatory Neural Networks (ONNs) are an emerging computing paradigm that encodes information in the phases of coupled oscillators. Traditionally, ONNs have been investigated using homogeneous frequency oscillators. However, physical hardware implementations are inherently subject to frequency mismatches, device variability, and nonuniformities.
Nil Dinç, Filip Sabo, Aida Todri‐Sanial   +2 more
wiley   +1 more source

Advancing Efficient Error Reduction in DNA Data Storage Systems with Deep Learning‐Based Denoising Models

Advanced Intelligent Discovery, EarlyView.
Deep learning‐based denoising models are applied to DNA data storage systems to enhance error reduction and data fidelity. By integrating DnCNN with DNA sequence encoding methods, the study demonstrates significant improvements in image quality and correction of substitution errors, revealing a promising path toward robust and efficient DNA‐based ...
Seongjun Seo, Anshula Tandon, Nguyen Kim Uyen, Quoc Nam Le, Jee‐Hyong Lee, Sung Ha Park   +5 more
wiley   +1 more source

Binarized Neural Network Comprising Quasi‐Nonvolatile Memory Devices for Neuromorphic Computing

Advanced Electronic Materials
This study presents a binarized neural network (BNN) comprising quasi‐nonvolatile memory (QNVM) devices that operate in a positive feedback loop mechanism and exhibit an extremely low subthreshold swing (≤ 5 mV dec−1) and a high on/off ratio (≥ 107).
Yunwoo Shin, Juhee Jeon, Kyoungah Cho, Sangsig Kim   +3 more
doaj   +1 more source

Revealing Protein–Protein Interactions Using a Graph Theory‐Augmented Deep Learning Approach

Advanced Intelligent Discovery, EarlyView.
This study presents a fast, cost‐efficient approach for classifying protein–protein interactions by integrating graph‐theory parametrization with deep learning (DL). Multiscale features extracted from graph‐encoded polarized‐light microscopy (PLM) images enable accurate prediction of binding strengths.
Bahar Dadfar, Gözde Kabay, Matthias Franzreb, Kody Whisnant, Nicholas A. Kotov, Joerg Lahann   +5 more
wiley   +1 more source

Large‐Scale and Highly Reliable Hopfield Neural Networks Using Vertical NAND Flash Memory for the In‐Memory Associative Computing

Advanced Intelligent Systems, EarlyView.
Large‐scale Hopfield neural networks (HNNs) for associative computing are implemented using vertical NAND (VNAND) flash memory. The proposed VNAND HNN with the asynchronous update scenario achieve robust image restoration performance despite fabrication variations, while significantly reducing chip area (≈117× smaller than resistive random‐access ...
Jin Ho Chang, Jae Seung Woo, Suk‐Kang Sung, Ki‐Whan Song, Woo Young Choi   +4 more
wiley   +1 more source

Ferroelectric Tunnel Junction Memristor Crossbar Array with Annealing Optimization for In‐Memory Computing

Advanced Intelligent Systems, EarlyView.
A 48 × 48 ferroelectric tunnel junction (FTJ) crossbar array is fabricated and optimized through postmetallization annealing, enabling stable polarization switching and reliable multilevel conductance programming. Half‐bias operation, accurate vector–matrix multiplication with less than 1% error, and CIFAR‐10 image classification with near‐software ...
Sangwook Youn, Hwiho Hwang, Hyungjin Kim
wiley   +1 more source

Formal Analysis of Deep Binarized Neural Networks [PDF]

Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence, 2018
Understanding properties of deep neural networks is an important challenge in deep learning. Deep learning networks are among the most successful artificial intelligence technologies that is making impact in a variety of practical applications. However, many concerns were raised about `magical' power of these networks.
openaire   +1 more source

Feature Disentangling and Combination Implemented by Spin–Orbit Torque Magnetic Tunnel Junctions

Advanced Intelligent Systems, EarlyView.
Spin–orbit torque magnetic tunnel junctions (SOT‐MTJs) enable efficient feature disentangling and integration in image data. A proposed algorithm leverages SOT‐MTJs as true random number generators to disentangle and recombine features in real time, with experimental validation on emoji and facial datasets.
Xiaohan Li, Yingqian Xu, Caihua Wan, Ran Zhang, Meike Hindenberg, Raik Hoffmann, Shiqiang Liu, Tianyi Zhang, Shilong Xiong, Dehao Kong, Jihao Xia, Fangshuo Gao, Zhuyang Nie, Thomas Kämpfe, Guoqiang Yu, Xiufeng Han   +15 more
wiley   +1 more source

An Intrusion Detection System for 5G SDN Network Utilizing Binarized Deep Spiking Capsule Fire Hawk Neural Networks and Blockchain Technology

Future Internet
The advent of 5G heralds unprecedented connectivity with high throughput and low latency for network users. Software-defined networking (SDN) plays a significant role in fulfilling these requirements. However, it poses substantial security challenges due
Nanavath Kiran Singh Nayak, Budhaditya Bhattacharyya   +1 more
doaj   +1 more source