Results 141 to 150 of about 8,034,918 (294)
SA-LoRA: Shared-A decoupled low-rank adaptation for class-incremental learning
Journal of King Saud University: Computer and Information SciencesParameter-efficient fine-tuning methods have shown promise for continual learning with pre-trained models, yet existing approaches either sacrifice performance or incur linear parameter growth with task count.
Xiaohuan Bing +2 more
doaj +1 more source
Learned Parameter Compression for Efficient and Privacy-Preserving Federated Learning
IEEE Open Journal of the Communications SocietyFederated learning (FL) performs collaborative training of deep learning models among multiple clients, safeguarding data privacy, security, and legal adherence by preserving training data locally.
Yiming Chen +3 more
doaj +1 more source
dynoGP: Deep Gaussian Processes for Dynamic System Identification
International Journal of Adaptive Control and Signal Processing, EarlyView.This work introduces a novel class of deep models for system identification, dynamical deep Gaussian processes, which combine the strengths of data‐driven methods, such as those based on neural network architectures, with the ability to output a probability distribution for uncertainty representation.
Alessio Benavoli +3 more
wiley +1 more source
Advanced Engineering Materials, EarlyView.Predicting extreme defects in additive manufacturing remains a key challenge limiting its structural reliability. This study proposes a statistical framework that integrates Extreme Value Theory with advanced process indicators to explore defect–process relationships and improve the estimation of critical defect sizes. The approach provides a basis for
Muhammad Muteeb Butt +8 more
wiley +1 more source
Targeted Active Learning for Bayesian Decision-Making
Active learning is usually applied to acquire labels of informative data points in supervised learning, to maximize accuracy in a sample-efficient way.
Kaski, Samuel +5 more
core +1 more source
What Do Large Language Models Know About Materials?
Advanced Engineering Materials, EarlyView.If large language models (LLMs) are to be used inside the material discovery and engineering process, they must be benchmarked for the accurateness of intrinsic material knowledge. The current work introduces 1) a reasoning process through the processing–structure–property–performance chain and 2) a tool for benchmarking knowledge of LLMs concerning ...
Adrian Ehrenhofer +2 more
wiley +1 more source
, 1974 A newsletter from Learning About Learning titled "The Academy Gazette.
Learning About Learning
core +1 more source
A Workflow to Accelerate Microstructure‐Sensitive Fatigue Life Predictions
Advanced Engineering Materials, EarlyView.This study introduces a workflow to accelerate predictions of microstructure‐sensitive fatigue life. Results from frameworks with varying levels of simplification are benchmarked against published reference results. The analysis reveals a trade‐off between accuracy and model complexity, offering researchers a practical guide for selecting the optimal ...
Luca Loiodice +2 more
wiley +1 more source
Simultaneous Parameter Learning and Bi-clustering for Multi-Response Models. [PDF]
Front Big Data, 2019 Yu M +3 more
europepmc +1 more source
Advanced Engineering Materials, EarlyView.Geometry‐driven thermal behavior in wire‐arc additive manufacturing (WAAM) influences microstructural evolution during nonequilibrium solidification of a chemically complex Fe–Cr–Nb–W–Mo–C nanocomposite system. By comparing different deposits configurations, distinct entropy–cooling rate correlations, segregation, and carbide evolution are revealed ...
Blanca Palacios +5 more
wiley +1 more source