Page 10: Research news on Machine learning methodologies

Machine learning methodologies encompass algorithmic frameworks and architectures for training, optimizing, and deploying models such as neural networks, transformers, diffusion models, and reinforcement learning agents. Work in this area develops new training objectives, curriculum schemes, speculative and efficient decoding, pruning and communication-reduction strategies, and biologically inspired or physics-informed architectures. The domain also includes safety preservation, unlearning, scaling laws, and specialized methods for vision, language, control, and scientific computing, aiming to improve performance, efficiency, robustness, and controllability of complex AI systems.

Machine learning & AI

Dialogue systems learn new words with fewer questions

Researchers at the University of Osaka have developed a mechanism that allows spoken dialog systems to learn new words through conversation without overwhelming users with repetitive questions. By optimizing when to ask a ...

Machine learning & AI

AI tool helps researchers treat child epilepsy

An artificial intelligence tool that can detect tiny, hard-to-spot brain malformations in children with epilepsy could help patients access life-changing surgery quicker, Australian researchers said on Wednesday.

page 10 from 23