Results 51 to 60 of about 221,728 (275)
Advanced Science, EarlyView.SpaBatch is an end‐to‐end multi‐slice spatial transcriptomics data integration framework. It simultaneously performs embedding learning, spatial feature denoising and reconstruction, batch effect correction, and spatial domain optimization, effectively correcting batch effects and achieving accurate 3D spatial domain identification.
Jinyun Niu +5 more
wiley +1 more source
Advanced Science, EarlyView.Reservoir computing in the physical domain promises an alternative, more energy‐efficient approach to machine learning. However, the correlation between mechanical design and computing power remains elusive. This study sheds light on this gap by repurposing a meta‐stable modular origami manipulator into an adaptive computing kernel that can perform ...
Jun Wang, Suyi Li
wiley +1 more source
Advanced Science, EarlyView.SETComp, a transfer learning model based on permutation‐invariance, is pre‐trained on single‐compound intervention data and fine‐tuned on complex system (e.g., natural products) data. The model achieves up to 93.86% accuracy on complex system‐cell‐gene association predictions, outperforming the baseline by up to 27.59%.
Boyang Wang +4 more
wiley +1 more source
Advanced Science, EarlyView.The paper proposes that the root cause of aging is the loss of anatomical goal‐directedness after development. Using evolutionary neural cellular automata simulations, the authors show that after the organism has reached its developmental homeostatic setpoint (the adult morphology), the absence of target state to pursue leads to a drifting anatomical ...
Léo Pio‐Lopez +2 more
wiley +1 more source
Deep adversarial attack on target detection systems
Artificial Intelligence and Machine Learning for Multi-Domain Operations Applications, 2019 Target detection systems identify targets by localizing their coordinates on the input image of interest. This is ideally achieved by labeling each pixel in an image as a background or a potential target pixel. Deep Convolutional Neural Network (DCNN) classifiers have proven to be successful tools for computer vision applications.
Uche Osahor, Nasser M. Nasrabadi
openaire +3 more sources
High‐Throughput Strategies for Streamlining Lipid Nanoparticle Development Pipeline
Advanced Science, EarlyView.This review highlights emerging state‐of‐the‐art high‐throughput strategies for optimising lipid nanoparticle formulation. By integrating combinatorial design, characterization, in vitro/in vivo screening, automation, and machine learning into a closed‐loop framework, it provides a roadmap to streamline discovery and accelerate the translation of ...
Lois Lam +3 more
wiley +1 more source
Advanced Science, EarlyView.A cost‐effective and scalable PCNN approach is developed for NIR model construction that has compatibility with multiple instruments and multiple crops. It is time and cost saving, rapid and nondestructive, small sample set based, various quality properties and extensible for breeding application in fresh maize, forage maize, rice, wheat, and barley ...
Jiang Shi +9 more
wiley +1 more source
Adversarial Examples to Fool Iris Recognition Systems [PDF]
, 2019 Sobhan Soleymani +3 more
openalex +3 more sources
Adversarially Trained End-to-End Korean Singing Voice Synthesis System [PDF]
, 2019 Juheon Lee +4 more
openalex +3 more sources