Neural Networks

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 …

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 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 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 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 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 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 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 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…

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…

A developer released Microcrad, a reimplementation of Andrej Karpathy's Micrograd automatic differentiation engine in C, designed for educational purposes to demonstrate backpropagation on scalars. The library uses refer…

Road trips offer mental health benefits by serving as a digital detox, activating feel-good hormones like oxytocin and dopamine, and creating new neural pathways through novel experiences, according to clinical psycholog…

Paradromics, a competitor to Neuralink, implanted its Connexus brain-chip in a Michigan woman with motor neuron disease to restore speech. The FDA-approved procedure at University of Michigan Health marks the startup's f…

Neuroscientists in Italy discovered that autobiographical memories are organized in the brain by temporal distance, with the right hippocampus encoding event identity and temporal distance, while frontopolar and retrospl…

Neuroscientist Vivienne Ming warns that outsourcing thinking to AI could weaken cognitive reserve, the brain's defense against dementia, especially in young people. She compares AI chatbots to GPS, citing studies showing…