Results 101 to 110 of about 124,149 (320)

A Holographic Sensor‐Integrated Deep Learning Framework for Noninvasive Assessment of Stored Red Blood Cell Quality

Advanced Sensor Research, EarlyView.
A holographic sensing‐integrated deep learning platform enables real‐time, label‐free assessment of red blood cell (RBC) quality during storage. By combining diffusion model‐based data augmentation and self‐supervised pretraining, the framework achieves high segmentation accuracy with minimal data.
Seonghwan Park, Hyunbin An, Abdur Rehman, Inkyu Moon   +3 more
wiley   +1 more source

Knowledge Transfer in Deep Reinforcement Learning via an RL-Specific GAN-Based Correspondence Function

IEEE Access
Deep reinforcement learning has demonstrated superhuman performance in complex decision-making tasks, but it struggles with generalization and knowledge reuse—key aspects of true intelligence. This article introduces a novel approach that modifies
Marko Ruman, Tatiana V. Guy
doaj   +1 more source

Leveraging Transfer Learning to Overcome Data Limitations in Czochralski Crystal Growth

Advanced Theory and Simulations, EarlyView.
A data‐driven framework combining Computational Fluid Dynamics (CFD) simulations and machine learning is proposed to model and optimize Czochralski crystal growth. Using different transfer learning strategies (Warm Start, Merged Training, and Hyperparameter Transfer) the study demonstrates improved predictions for Ge and GaAs growth from Si‐trained ...
Milena Petkovic, Natasha Dropka, Xia Tang, Janina Zittel   +3 more
wiley   +1 more source

Mode Regularized Generative Adversarial Networks

, 2017
Although Generative Adversarial Networks achieve state-of-the-art results on a variety of generative tasks, they are regarded as highly unstable and prone to miss modes.
Bengio, Yoshua, Che, Tong, Jacob, Athul Paul, Li, Wenjie, Li, Yanran   +4 more
core  

Painting Peptides With Antimicrobial Potency Through Deep Reinforcement Learning

Advanced Science, EarlyView.
AMPainter is a powerful design model for ’painting’ the antimicrobial potency on any given peptide sequence, based on the strategy of virtual directed evolution and deep reinforcement learning. Abstract In the post‐antibiotic era, antimicrobial peptides (AMPs) are considered ideal drug candidates because of their lower likelihood of inducing resistance.
Ruihan Dong, Qiushi Cao, Chen Song
wiley   +1 more source

Generative adversarial synthetic neighbors-based unsupervised anomaly detection

Scientific Reports
Anomaly detection is crucial for the stable operation of mechanical systems, securing financial transactions, and ensuring network security, among other critical areas.
Lan Chen, Hong Jiang, Lizhong Wang, Jun Li, Manhua Yu, Yong Shen, Xusheng Du   +6 more
doaj   +1 more source

Multi-Source Medical Image Fusion Based on Wasserstein Generative Adversarial Networks

IEEE Access, 2019
In this paper, we propose the medical Wasserstein generative adversarial networks (MWGAN), an end-to-end model, for fusing magnetic resonance imaging (MRI) and positron emission tomography (PET) medical images.
Zhiguang Yang, Youping Chen, Zhuliang Le, Fan Fan, Erting Pan   +4 more
doaj   +1 more source

Precision‐Arranged DNA Origami Plasmonic Nanoantennas for Multidimensional Smart‐Warning of Weightlessness Induced Bone Loss

Advanced Science, EarlyView.
It is synthesized precision‐arranged DNA origami plasmonic nanoantennas for multiplexed and intelligent warning of bone loss induced by microgravity and radiation. The ordered nanoantennas simultaneously and accurately detected calcium ions, interleukin‐6, and microRNA‐214 in serum from mice exposed to microgravity and radiation, with performance ...
Yufan Ling, Xuan Qin, Weijia Sun, Fan Yue, Yiwei Wang, Di Fan, Haoyuan Xu, Ruao Xie, Jiawei Zhang, Jianwei Li, Bingyan Li, Yang Yang, Yingxian Li, Houyu Wang, Guangming Zhou   +14 more
wiley   +1 more source

Generative Adversarial Networks: Recent Developments [PDF]

, 2019
10 ...
Maciej Zięba, Maciej Zamorski, Adrian Zdobylak, Jerzy Świątek   +3 more
openaire   +3 more sources

Controllable Generation of Pathogen‐Specific Antimicrobial Peptides Through Knowledge‐Aware Prompt Diffusion Model

Advanced Science, EarlyView.
KPPepGen is a knowledge‐aware prompt diffusion model for the controllable generation of pathogen‐specific AMPs. It outperforms existing methods and is capable of simultaneously generating peptides for distinct pathogens, demonstrating superior performance with favorable properties and docking efficacy.
Yongkang Wang, Menglu Li, Feng Huang, Minyao Qiu, Wen Zhang   +4 more
wiley   +1 more source