Conjugate gradient methods form a class of iterative algorithms that are highly effective for solving large‐scale unconstrained optimisation problems. They achieve efficiency by constructing search ...

Anti-forgetting representation learning method reduces the weight aggregation interference on model memory and augments the representation performance.

Federated Learning (FL) allows for privacy-preserving model training by enabling clients to upload model gradients without exposing their personal data. However, the decentralized nature of FL ...

Analysis and application of numerical methods for solving large systems of linear equations, which often represent the bottleneck when computing solutions to equations arising in fluid mechanics, ...