Multistable Physical Neural Networks
This article presents the integration of mechanical bistability into physical neural networks (PNNs), enabling memory retention and bridging computation with physical action. By mapping the equilibrium states of bistable, liquid‐filled chambers, it explores stability and introduces global and local training algorithms.
Ben‐Haim Eran+3 more
wiley +1 more source
Land cover classification of high-resolution remote sensing images based on improved spectral clustering. [PDF]
Wu S, Cao JM, Zhao XY.
europepmc +1 more source
The determinant of the Laplacian matrix of a quaternion unit gain graph [PDF]
Ivan Kyrchei+2 more
openalex +1 more source
Sparse graph signals – uncertainty principles and recovery
ABSTRACT We study signals that are sparse either on the vertices of a graph or in the graph spectral domain. Recent results on the algebraic properties of random integer matrices as well as on the boundedness of eigenvectors of random matrices imply two types of support size uncertainty principles for graph signals.
Tarek Emmrich+2 more
wiley +1 more source
Network Diffusion-Constrained Variational Generative Models for Investigating the Molecular Dynamics of Brain Connectomes Under Neurodegeneration. [PDF]
Xie J, Tandon R, Mitchell CS.
europepmc +1 more source
Human Cortico‐Cerebellar Dynamics During Motor Error Processing After Stroke
Human cortico‐cerebellar interactions during motor error correction were explored using synchronized cerebellar and EEG recordings. Results highlight centro‐parietal error positivity, fronto‐centro‐parietal desynchronization, and alpha/low‐beta cortico‐cerebellar coherence, underscoring bidirectional neural interactions in motor error processing ...
Nitesh Singh Malan+5 more
wiley +1 more source
Bipartite Fault-Tolerant Consensus Control for Multi-Agent Systems with a Leader of Unknown Input Under a Signed Digraph. [PDF]
Liu A, Zhang W, Yue D, Chen C, Shi J.
europepmc +1 more source
Deep‐Diffeomorphic Networks for Conditional Brain Templates
We have built on recent deep‐learning template generation approaches using a diffeomorphic framework to create a purely geometric conditional brain template construction method. We assessed the effectiveness of our method and recent approaches at capturing age‐dependent anatomical differences, demonstrating that further refinement is required to ...
Luke Whitbread+4 more
wiley +1 more source
Adaptive connectivity control in networked multi-agent systems: A distributed approach. [PDF]
Križmančić M, Bogdan S.
europepmc +1 more source
SCT‐BEM for Transient Heat Conduction and Wave Propagation in 2D Thin‐Walled Structures
ABSTRACT Traditional boundary element method (BEM) faces significant challenges in addressing dynamic problems in thin‐walled structures. These challenges arise primarily from the complexities of handling time‐dependent terms and nearly singular integrals in structures with thin‐shapes.
Xiaotong Gao, Yan Gu
wiley +1 more source