Artificial neural networks

Neural Networks Uncover Human Decision-Making Patterns through Symbolic Regression

Researchers have made a breakthrough in understanding human decision-making by combining artificial neural networks (ANNs) with symbolic regression. This approach allows for the extraction of an expressive and interpretable model that specifies how individuals evaluate decision-relevant information during choice. The model was able to account for behavior in the researchers&

Advances in Brain Tract Segmentation Using Hybrid Convolutional Neural Networks

Researchers at the Department of Electronics and Communication Engineering have made a breakthrough in brain tract segmentation using a novel hybrid convolutional neural network (CNN) architecture. The proposed method, called DISAU-Net, combines the benefits of Inception-ResNet-V2 and densely connecting convolutional modules to achieve unprecedented accuracy in segmenting white matter fiber

Artificial neural networks

Artificial Neural Networks Revolutionize Precision Agriculture

Researchers from Universidad Distrital Francisco Jose de Caldas in Colombia have found that artificial neural networks (ANNs) can significantly improve precision agriculture by analyzing agricultural data and making informed decisions. The study, published in the journal Informatics, highlights the benefits of ANNs in pest detection, disease classification, crop state assessment,

Artificial neural networks

Energy-Efficient Prediction of Carbon Deposition in DRM Processes Through Optimized Neural Network Modeling

Researchers from Tsinghua University have published a groundbreaking study on the energy efficiency of methane dry reforming (DRM) processes, a promising method for converting greenhouse gases into syngas. To overcome the limitations of conventional neural network models, the team developed a novel optimization framework using radial basis function (RBF) neural

Artificial neural networks

Accelerated DGTD Method for Electromagnetic Analysis Improves Computational Efficiency

Researchers from Tsinghua University have proposed an accelerated memory efficient discontinuous Galerkin time-domain (DGTD) method utilizing the hybrid time integration scheme based on Runge-Kutta (RK) time stepping and radial basis function neural network (RBFNN) prediction. This method addresses the computational inefficiency arising from complex boundary conditions and multiscale features in

Artificial neural networks

Researchers from Tsinghua University Detail Research in Networks

In a breakthrough study, researchers from Tsinghua University in Beijing, China have made significant advancements in the field of optical computing. By leveraging artificial intelligence and on-chip deep diffractive neural network (D^2NN) technology, the team has successfully demonstrated an end-to-end truth table direct mapping approach for highly parallel optical

Artificial neural networks

Artificial Neural Networks for Estimating Fatigue Life of Steel Components

Researchers at the University of Rijeka have developed a surrogate artificial neural network (ANN) model to estimate the fatigue life of steel components with stress concentrators. The model, trained on data generated from a computational finite element-based (FE-based) model, can accurately predict the number of load cycles to failure. This

Artificial neural networks

Research Uncovers Efficient Neural Network Approach for Predicting Energy Performance in Commercial Buildings

A new report from researchers at the University of Perugia reveals a simplified neural network approach to predict energy and thermal performance in commercial buildings, enhancing the applicability of artificial intelligence techniques. By utilizing the EnergyPlus dynamic simulation software, the study demonstrates a computationally lightweight and scalable solution for performance

Artificial neural networks

Nuclear Quantum Effects Significantly Influence Water Properties

New research in Chemical Physics has revealed that nuclear quantum effects play a substantial role in the structure, dynamics, and phase behavior of water. The study, conducted by researchers at the University of Vienna, employed machine-learned neural network potentials to perform large-scale path-integral molecular dynamics simulations. The findings suggest that

Artificial neural networks

Breakthrough in Materials Research: Discovering New High-Pressure Phases

Researchers at Purdue University have made a groundbreaking discovery in materials science, leveraging the power of graph neural networks and high-throughput density functional theory (DFT) simulations to identify 28 new high-pressure stable phases and confirm 18 pressure-induced phase transitions. This innovative approach has significantly accelerated the discovery process, which was

Artificial neural networks

Binary Neural Networks Show Promise in Cybersecurity Applications

Researchers at Loughborough University have made a significant discovery in the field of cybersecurity, finding that Binary Neural Networks (BNNs) can significantly reduce computational complexity while maintaining accuracy in resource-constrained environments. This breakthrough has the potential to revolutionize the way we approach cybersecurity in areas such as autonomous systems, industrial

Artificial neural networks

Researchers Develop Neural Network Method for Solving Time Fractional Diffusion Equations

Researchers from the Qingdao University of Technology have made a significant breakthrough in thermodynamics by developing a neural network method to solve time-fractional diffusion equations. This innovative approach combines machine learning techniques with the Method of Lines to provide an efficient and accurate solution to complex diffusion problems. The researchers&

See all