BIOENGINEER

New Contribution Scoring Method Boosts Federated Learning Accuracy

Researchers in India have developed ASHA, a federated learning algorithm that weights each client's updates by a dynamic ...
BIOENGINEER

Genetic Algorithms Meet LoRA: New Study Tests Whether Smarter Search Really Beats Simple Tuning

Fine-tuning large language models has become one of the most expensive rituals in modern artificial intelligence. Every time ...
Nature

Feature Selection Techniques in Machine Learning Systems articles from across Nature Portfolio

Feature selection (FS) is a critical step in hyperspectral image (HSI) classification, essential for reducing data dimensionality while preserving classification accuracy. However, FS for HSIs remains ...
VentureBeat

DeepMind’s new inference-time scaling technique improves planning accuracy in LLMs

Inference-time scaling is one of the big themes of artificial intelligence in 2025, and AI labs are attacking it from different angles. In its latest research paper, Google DeepMind introduced the ...