Neural subspace reorganization reflects value-based decision-making. [PDF]
Li H +4 more
europepmc +1 more source
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
Error semitransparent universal control of a bosonic logical qubit. [PDF]
Roy S, Wetherbee OC, Fatemi V.
europepmc +1 more source
Understanding emotional responses to music using machine learning: evidence from a public dataset. [PDF]
Sun H.
europepmc +1 more source
Enhancing generalized spectral clustering with embedding Laplacian graph regularization
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
Multimodal subspace independent vector analysis effectively captures latent relationships between brain structure and function. [PDF]
Li X +4 more
europepmc +1 more source
Boosted unsupervised feature selection for tumor gene expression profiles
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
Manifold-constrained plasticity enables stable learning in recurrent neural circuits. [PDF]
Godin C, Thivierge JP.
europepmc +1 more source
A Deep Nonlinear Subspace Modeling and Reconstruction for Diffusion-Weighted Imaging Using Denoising Auto-Encoder. [PDF]
Glaser J +4 more
europepmc +1 more source
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

