Researchers isolate memorization from problem-solving in AI neural networks

The researchers discovered that this separation proves remarkably clean. In a preprint paper released in late October, they ...
eLife

Extracting Value Coding Features from Individual Serotonin Neurons

The authors used a Bayesian modeling framework to fit behavior and serotonin neuron activity to reward history across multiple timescales. A key goal was to distinguish value coding from other ...
eLife

The time course of visuo-semantic representations in the human brain is captured by combining vision and language models

The human visual system provides us with a rich and meaningful percept of the world, transforming retinal signals into visuo-semantic representations. For a model of these representations, here we ...
IEEE

A Two-Branch Neural Network for Gas-Bearing Prediction Using Latent Space Adaptation for Data Augmentation—An Application for Deep Carbonate Reservoirs

Abstract: Deep learning has been utilized for gas-bearing prediction in recent years due to its powerful nonlinear fitting capacity; however, the scarcity of log labels severely restricts its ...
Chemistry World

Neural network trained to classify crystal structure errors in MOF and other databases

A neural network promises to improve the fidelity of crystal structure databases for metal–organic frameworks (MOF) by detecting and classifying structural errors. 1 The approach, which flags entries ...
chromatographyonline

Standardizing Statistical Tools for “Omics’: Best Practices Using R and Python

A global team led by Michal Holčapek, professor of analytical chemistry at the Faculty of Chemical Technology, UPCE, Pardubice (Czech Republic), and Jakub Idkowiak, a research associate from KU Leuven ...
C&EN

High-Precision Microscale Particulate Matter Prediction in Diverse Environments Using a Long Short-Term Memory Neural Network and Street View Imagery

Beijing Key Laboratory of Big Data Technology for Food Safety, School of Computer Science and Engineering, Beijing Technology and Business University, Beijing 100048, China State Key Laboratory of ...
C&EN

SlaKoNet: A Unified Slater-Koster Tight-Binding Framework Using Neural Network Infrastructure for the Periodic Table

Department of Materials Science and Engineering, Whiting School of Engineering, The Johns Hopkins University, Baltimore, Maryland 21218, United States Department of Electrical and Computer Engineering ...
IEEE

Adaptive Neural-Network Sliding Mode Admissible Consensus for Discrete-Time Singular Multi-Agent Systems Under Stochastic Topology

Abstract: The information interaction between agents in this paper is described using Markov switching topology, and an adaptive neural-network sliding mode (ANNSM) controller is proposed to address ...