Results 191 to 200 of about 14,534,285 (294)

Neural subspace reorganization reflects value-based decision-making. [PDF]

open access: yesiScience
Li H   +4 more
europepmc   +1 more source

An Auditable and Interpretable Fault‐Diagnosis Classifier Based on a Learning Probabilistic Boolean Network

open access: yesArtificial Intelligence for Engineering, EarlyView.
A Learning Probabilistic Boolean Network circuit diagnoses Tennessee Eastman Process faults with accuracy statistically indistinguishable from the strongest comparators and, unlike them, can be formally audited: a solver exposes safety defects that test metrics miss, and one residual predicate resolves the hardest fault.
Pedro Juan Rivera Torres   +2 more
wiley   +1 more source

Enhancing generalized spectral clustering with embedding Laplacian graph regularization

open access: yesCAAI Transactions on Intelligence Technology, EarlyView.
Abstract An enhanced generalised spectral clustering framework that addresses the limitations of existing methods by incorporating the Laplacian graph and group effect into a regularisation term is presented. By doing so, the framework significantly enhances discrimination power and proves highly effective in handling noisy data.
Hengmin Zhang   +5 more
wiley   +1 more source

Boosted unsupervised feature selection for tumor gene expression profiles

open access: yesCAAI Transactions on Intelligence Technology, EarlyView.
Abstract In an unsupervised scenario, it is challenging but essential to eliminate noise and redundant features for tumour gene expression profiles. However, the current unsupervised feature selection methods treat all samples equally, which tend to learn discriminative features from simple samples.
Yifan Shi   +5 more
wiley   +1 more source

LLM‐Powered Data Synthesis on Blockchain for Fusion Isomerism Learning in Heterogeneous Federated Systems

open access: yesCAAI Transactions on Intelligence Technology, EarlyView.
ABSTRACT Severe data starvation, architectural heterogeneity and Byzantine vulnerabilities fundamentally impede the deployment of robust multiclass classification models in decentralised edge environments. To address these intertwined challenges, we propose fusion isomerism learning (FusionIL), a secure and domain‐agnostic framework that ...
Zhihao Hao   +5 more
wiley   +1 more source

Home - About - Disclaimer - Privacy