Neural Networks

A study published in Social Cognitive and Affective Neuroscience found that lonely individuals perceive themselves as less empathic, but Loving Kindness Meditation did not increase empathy despite reducing loneliness. Th…

A new essay provides a framework for evaluating neurotechnology approaches, outlining key questions about brain state measurements and their relevance to applications. The author, drawing on expert conversations, aims to…

A developer created GNEISS, a CLI tool that uses graph neural networks to detect architectural decay in Java repositories. The tool parses imports, builds a dependency graph, and runs it through a neural network pipeline…

Researchers improved short-range phytoplankton forecasts in the North-West European Shelf by up to 30% by assimilating neural network-predicted surface nitrate into the Met Office forecasting system, addressing biases fr…

Researchers Antoine Pesenti and Aidan O'Sullivan combined deep neural networks with explainable AI techniques to analyze electricity price formation across 39 European bidding zones, identifying renewable sources, partic…

Jozef Skakala's arXiv preprint (2508.10178) proposes using a computationally cheap ensemble of neural networks to estimate marine carbon pools across the North-West European Shelf (NWES). The deep ensemble, trained on a …

A new study on arXiv presents an experimental analysis of neural network-based image classification on the CIFAR-10 dataset, comparing fully connected and convolutional architectures. The convolutional network achieved 7…

A new study comparing Vision Transformers and CNNs for face presentation attack detection found that pretrained Vision Transformers reduce demographic bias and improve accuracy. The DeiT-S model achieved 97.27% accuracy …

Researchers propose Artemis, a region-level causal framework for multimodal neuroimaging that adjusts for demographic confounders like age and sex at each brain region independently. The method improves graph neural netw…

Researchers have developed a speech-driven end-to-end model for discriminating among Chinese dialects, combining MFCC features with word-level embeddings via a CNN. The approach outperforms state-of-the-art methods on tw…

Researchers introduced Gaussian Mixture Attention (GMA), a probabilistic attention mechanism that replaces pairwise query-key comparisons with routing through K learned Gaussian mixture components, achieving linear-time …

Researchers propose RGNet, a neural network architecture inspired by the renormalization group, to address class imbalance and noise in fault diagnosis. The model hierarchically compresses feature spaces and introduces R…

Researchers introduced Ghost Attractor Networks, a dynamical decoder that uses basin-structured latent representations for closed-loop sequential generation. The 2.3-million-parameter Ghost matched the offline accuracy o…

Researchers at arXiv published a retrospective on SWAVE, a complex-valued recurrent language model, revealing that its Resonance Head suffered from a failure mode called cos-domination collapse, which was resolved by ado…

Researchers propose a K-Hop Gaussian diffusion kernel to enhance graph neural networks, improving information propagation in noisy or complex graphs. The method outperforms traditional message-passing GNNs and existing d…

Researchers established a mathematical link between shock-wave theory and symmetry-reduced stochastic gradient descent for artificial neural networks, showing that after quotienting parameter symmetries and applying coar…

Researchers introduced CAOA, a method that integrates point cloud completion with symmetry-aware pose estimation to align CAD models to objects in indoor RGB-D scans. On the Scan2CAD benchmark, CAOA achieved a 17% accura…

A new geometric framework explains how transformer attention reconfigures token embeddings layer by layer, driving semantically related tokens into clusters. The process reduces to two operators acting in a single vector…

A Microsoft researcher built a neural network using goats, bridges, and ice ramps in Age of Empires II to critique AI research methods. His analysis of 315 papers found over half already assume language models have human…

Paradromics has implanted its Connexus brain-computer interface in the first participant of its FDA-approved clinical study, a Michigan woman with motor neuron disease who has lost the ability to speak clearly. The devic…