Scientists develop predictive roadmap to boost performance in next-gen spintronics

Chiral 2D metal halide perovskites (MHPs) are among the most promising materials for future technologies that exploit the ...
Microsoft

Graph Convolutional Matrix Completion

We consider matrix completion for recommender systems from the point of view of link prediction on graphs. Interaction data such as movie ratings can be represented by a bipartite user-item graph with ...
GitHub

MixHop and N-GCN

Recent methods generalize convolutional layers from Euclidean domains to graph-structured data by approximating the eigenbasis of the graph Laplacian. The computationally-efficient and broadly-used ...
the-decoder

AI-generated CUDA kernels outperform PyTorch in several GPU-heavy machine learning benchmarks

A team at Stanford has shown that large language models can automatically generate highly efficient GPU kernels, sometimes outperforming the standard functions found in the popular machine learning ...
Nature

Brain tumor detection from images and comparison with transfer learning methods and 3-layer CNN

The healthcare industry has been rapidly transformed by technological advances in recent years, and an important component of this transformation is artificial intelligence (AI) technology. AI is a ...
C&EN

Precise Surface Profiling at the Nanoscale Enabled by Deep Learning

Materials Research Laboratory, University of Illinois, Urbana, Illinois 61801, United States Department of Mechanical Science and Engineering, University of Illinois, Urbana, Illinois 61801, United ...
IEEE

Application of Graph Learning With Multivariate Relational Representation Matrix in Vehicular Social Networks

Abstract: The essence of connection in vehicle network is the social relationship between people, and thus Vehicular Social Networks (VSNs), characterized by social aspects and features, can be formed ...
IEEE

A Multi-Dimensional Graph Convolution Network for EEG Emotion Recognition

Abstract: Due to the changeable, high-dimensional, nonstationary, and other characteristics of electroencephalography (EEG) signals, the recognition of EEG signals is mostly limited to independent ...
Nature

A method of radar echo extrapolation based on dilated convolution and attention convolution

Nowcasting was first proposed by Browning 1 in 1982, and it is mainly used in early warning of disasters like thunderstorms, severe convective weather, rainstorm, and snowstorm. Accurate short-term ...
InfoQ

MIT Researchers Open-Source Approximate Matrix Multiplication Algorithm MADDNESS

Researchers at MIT's Computer Science & Artificial Intelligence Lab (CSAIL) have open-sourced Multiply-ADDitioN-lESS (MADDNESS), an algorithm that speeds up machine learning using approximate matrix ...
Frontiers

Motor Imagery EEG Signal Recognition Using Deep Convolution Neural Network

Brain computer interaction (BCI) based on EEG can help patients with limb dyskinesia to carry out daily life and rehabilitation training. However, due to the low signal-to-noise ratio and large ...