eLife

Human EEG and artificial neural networks reveal disentangled representations and processing timelines of object real-world size and depth in natural images

Neural and computational evidence reveals that real-world size is a temporally late, semantically grounded, and hierarchically stable dimension of object representation in both human brains and ...
Frontiers

Biological detail and graph structure in network neuroscience

Representing the brain as a complex network typically involves approximations of both biological detail and network structure. Here, we discuss the sort of biological detail that may improve network ...
eLife

A theory and recipe to construct general and biologically plausible integrating continuous attractor neural networks

Department of Brain and Cognitive Sciences & McGovern Institute, MIT, Cambridge, United States Integrative Computational Neuroscience Center and Yang-Tan Collective, MIT, Cambridge, United States ...
C&EN

The Dynamic Connection Layer (DCL): Enhancing Topological Representation in Chemical Graph Neural Networks

Creative Commons (CC): This is a Creative Commons license. Attribution (BY): Credit must be given to the creator. Non-Commercial (NC): Only non-commercial uses of the work are permitted. In ...
Oak Ridge National Lab

GSplit: Scaling Graph Neural Network Training on Large Graphs via Split-Parallelism...

Proceedings of The Eighth Annual Conference on Machine Learning and Systems Graph neural networks (GNNs), an emerging class of machine learning models for graphs, have gained popularity for their ...
IEEE

Self-representation-based Generative Graph Neural Networks for End-to-End Link Prediction

Abstract: Recently, deep neural networks have revolutionized the field of link prediction, and the state-of-the-art works are typically subgraph-based discriminative methods, which construct features ...
www.cs.cmu.edu

Grounding Neural Inference with Satisfiability Modulo Theories: Leveraging Theory Solvers for Machine Learning

Modern AI excels at pattern recognition but suffers when faced with logical reasoning tasks. What happens when we ask a neural network to solve a Sudoku puzzle from an image, verify a mathematical ...
Frontiers

Explainable graph neural network based on metabolic brain imaging for differential diagnosis of parkinsonism

Background: Accurate differentiation of parkinsonian syndromes remains challenging due to overlapping clinical manifestations and subtle neuroimaging variations. This study introduces an explainable ...