News

Johns Hopkins University Applied Physics Laboratory1d
Johns Hopkins APL Develops Innovative Platform for Traumatic Brain Injury Research
A team of researchers from APL and the Johns Hopkins Bloomberg School of Public Health is developing next-generation brain organoid platforms to better understand the effects of mild blast-induced ...
Scientists Use A.I. to Mimic the Mind, Warts and All
To better understand human cognition, scientists trained a large language model on 10 million psychology experiment questions ...
IEEE2d
Graph Learning with Low-rank and Diagonal Structures: A Riemannian Geometric Approach - IEEE Xplore
We study the problem of learning graphs in Gaussian graphic models by assuming that the underlying precision matrix has a "low-rank and diagonal" (LRaD) structure. This assumption enjoys a latent ...
Communications of the ACM2d
Thinking Fast and Slow in Human and Machine Intelligence
To flexibly and robustly handle diverse problems, AI systems can leverage dual-process theories of human cognition that ...
AI predicts material properties using electron-level information without costly quantum mechanical computations
Researchers in Korea have developed an artificial intelligence (AI) technology that predicts molecular properties by learning ...
IEEE3d
Unsupervised Learning of Graph Matching With Mixture of Modes via Discrepancy Minimization - IEEE Xplore
Graph matching (GM) has been a long-standing combinatorial problem due to its NP-hard nature. Recently (deep) learning-based approaches have shown their superiority over the traditional solvers while ...