Results 111 to 120 of about 29,955 (264)
Generating Natural Adversarial Examples
CoRR, 2017 Due to their complex nature, it is hard to characterize the ways in which machine learning models can misbehave or be exploited when deployed. Recent work on adversarial examples, i.e. inputs with minor perturbations that result in substantially different model predictions, is helpful in evaluating the robustness of these models by exposing the ...
Zhengli Zhao +2 more
openaire +4 more sources
Composition‐Aware Cross‐Sectional Integration for Spatial Transcriptomics
Advanced Intelligent Discovery, EarlyView.Multi‐section spatial transcriptomics demands coherent cell‐type deconvolution, domain detection, and batch correction, yet existing pipelines treat these tasks separately. FUSION unifies them within a composition‐aware latent framework, modeling reads as cell‐type–specific topics and clustering in embedding space.
Qishi Dong +5 more
wiley +1 more source
Synthesizing Robust Adversarial Examples
CoRR, 2017 Standard methods for generating adversarial examples for neural networks do not consistently fool neural network classifiers in the physical world due to a combination of viewpoint shifts, camera noise, and other natural transformations, limiting their relevance to real-world systems.
Anish Athalye +3 more
openaire +4 more sources
Harnessing Machine Learning to Understand and Design Disordered Solids
Advanced Intelligent Discovery, EarlyView.This review maps the dynamic evolution of machine learning in disordered solids, from structural representations to generative modeling. It explores how deep learning and model explainability transform property prediction into profound physical insight.
Muchen Wang, Yue Fan
wiley +1 more source
AI‐Driven Cancer Multi‐Omics: A Review From the Data Pipeline Perspective
Advanced Intelligent Discovery, EarlyView.The exponential growth of cancer multi‐omics data brings opportunities and challenges for precision oncology. This review systematically examines AI's role in addressing these challenges, covering generative models, integration architectures, Explainable AI for clinical trust, clinical applications, and key directions for clinical translation.
Shilong Liu, Shunxiang Li, Kun Qian
wiley +1 more source
Advanced Intelligent Discovery, EarlyView.Materials informatics and autonomous experimentation are transforming the discovery of organic molecular crystals. This review presents an integrated molecule–crystal–function–optimization workflow combining machine learning, crystal structure prediction, and Bayesian optimization with robotic platforms.
Takuya Taniguchi +2 more
wiley +1 more source
Advanced Intelligent Discovery, EarlyView.Machine learning serves as a central engine for the intelligent characterization of two‐dimensional materials by integrating multimodal techniques, including optical microscopy, spectroscopy, electron microscopy, and scanning probe microscopy (SPM). This unified framework enables automated, high‐throughput, and quantitative extraction of structural ...
Zhi‐Long Cao, Jia‐Xu Yan
wiley +1 more source
Explaining and Harnessing Adversarial Examples
, 2014 Several machine learning models, including neural networks, consistently misclassify adversarial examples---inputs formed by applying small but intentionally worst-case perturbations to examples from the dataset, such that the perturbed input results in the model outputting an incorrect answer with high confidence.
Ian J. Goodfellow +2 more
openaire +3 more sources
A Generative AI Framework to Predict Cardiomyocyte Contraction Function From Single Static Images
Advanced Intelligent Discovery, EarlyView.A single static hiPSC‐cardiomyocyte image is fed into a U‐Net‐GAN framework, which directly predicts a pixel‐resolved contraction heatmap without time‐lapse imaging. StyleGAN2‐generated synthetic cell–heatmap pairs augment training, improving prediction fidelity (SSIM = 0.84).
Andrew Kowalczewski +5 more
wiley +1 more source
Boosting adversarial robustness via feature refinement, suppression, and alignment
Complex & Intelligent SystemsDeep neural networks are vulnerable to adversarial attacks, bringing high risk to numerous security-critical applications. Existing adversarial defense algorithms primarily concentrate on optimizing adversarial training strategies to improve the ...
Yulun Wu +6 more
doaj +1 more source