New software toolbox enables brain-like models to learn directly from data

Researchers have developed a powerful new software toolbox that allows realistic brain models to be trained directly on data.
IEEE

Overcoming Client Data Deficiency in Federated Learning by Exploiting Unlabeled Data on the Server

Abstract: Federated Learning (FL) is a distributed machine learning paradigm involving multiple clients to train a server model. In practice, clients often possess limited data and are not always ...
EurekAlert!

Geophysical-machine learning tool for continuous subsurface geomaterials characterization

Researchers utilize 2D electrical resistivity imaging and borehole data to estimate the N60-value of soils with k-means clustering technique Thailand's northern regions, characterized by complex ...
IEEE

PurifyFL: Non-Interactive Privacy-Preserving Federated Learning Against Poisoning Attacks Based on Single Server

Abstract: Privacy-preserving federated learning (PPFL) allows multiple users to collaboratively train models on local devices without the the risk of privacy leakage ...
GitHub

Machine learning server fails on search

Rolled back to 2.0.1 and used the same term - works. Log from machine learning server: [Nest] 35 - 10/18/2025, 11:23:07 AM ERROR [Api:ErrorInterceptor~v5y7xgni ...
C&EN

Machine Learning-Based Excited-State Reactive Force Field: A New Approach for Modeling the Photodissociation Dynamics of 2-Fluorothiophenol

Institute of Theoretical Chemistry, College of Chemistry, Jilin University, Changchun 130023, China ...