Neural Networks news and analysis on Web Pulse: 1652 curated articles tracking the latest Neural Networks developments, tools, and research, updated continuously from vetted sources.
WIPSNet, a 3D ResNet operating on stacked continuous wavelet transform scalograms of overnight impedance pneumography (IP) signals, achieved an AUC of 0.783 ± 0.026 for night-level paediatric wheeze classification, accor…
A study of hZACH-ViT, a compact Vision Transformer with Euclidean, Poincaré, and spherical prototype heads, found that reducing Poincaré curvature from c=1 to c=0.1 improved clean MacroF1 in all 15 paired seed-dataset co…
Researchers introduced WOMBAT, a benchmark of 14 whitebox graph neural networks (GNNs) whose message-passing weights are hand-set to detect a specific SMARTS motif, providing attribution ground truth for evaluating expla…
Developer Ben Houston released three-dlss-nr, a Three.js port of maanHimself's OpenDLSS-NR that runs the 71-block DLSS 5 neural rendering network as TSL compute kernels inside a WebGPURenderer with no CPU readback. The p…
Researchers from Carnegie Mellon, MIT, NYU, and Stanford built an AI called Ataraxos that beat four-time Stratego world champion Pim Niemeijer 15 games to one with four draws, using a second neural network that estimates…
A September 30, 2026 arXiv paper reports that major gains in non-invasive brain-to-text decoding are largely reproducible without any brain data, because fixed-length windows starting at each word implicitly leak word-du…
A data-free physics-informed neural operator for level-set interface advection, trained only on the transport residual and a geometric constraint with no reference solutions, reached 1.614 +/- 0.067% relative L2 error on…
Researchers introduced Continually-Recyclable Unit-Gating (CRUG), a continual learning method for dynamical systems reconstruction that achieves zero forgetting while conserving network capacity, according to an arXiv pa…
Researchers introduced the Function-Space Transformer (FST), a framework that learns from functions via a spatially adaptive continuous latent representation, storing features at anchors whose locations are predicted fro…
Researchers introduced Spatial Lifting (SL), a method that lifts 2D image inputs into a higher-dimensional space and processes them with networks such as a 3D U-Net, according to the arXiv paper 2610.00017v1. The authors…
A developer released Sovereign-NB, a bare-metal x86-64 neural inference appliance written in Rust that boots as a UEFI application and serves fixed-size input frames over a UART stream. The runtime runs two integer-only …
A solo developer published OpenDLSS-NR, an open-source Vulkan reimplementation of NVIDIA's DLSS 5 neural rendering network that the developer says matches the original byte-for-byte and runs on RTX 40 hardware NVIDIA loc…
An open-source project called ClashRoyaleAi published a browser demo in which a neural network with a few thousand weights, trained with the REINFORCE policy-gradient method, learns to place a single defending card again…
Researchers at the Weizmann Institute of Science in Rehovot, Israel, led by Michal Irani, built an AI "brain decoder" that reconstructs what a person is looking at from high-resolution fMRI scans and can also predict bra…
Functional ultrasound imaging (fUSI) can deliver up to 10 times higher linear resolution and 1000 times more voxels than functional MRI while requiring no magnet, according to a deep dive by Patrick Mineault, who publish…
A developer released OpenDLSS-NR, a Vulkan reimplementation of Nvidia's DLSS 5 Neural Rendering network that runs bit-exact against the original, matching all 75 block boundaries byte for byte. The project reproduces the…
A study of K-interv examines how quantizing the softmax in Transformer attention during pretraining changes both the forward computation and the gradients that train the model, as low-precision Transformer systems increa…
A new arXiv paper (2609.36172v1) reports that VGG16 achieved 89.55% validation accuracy in recognizing topological relationships between objects in images, outperforming traditional models including Naive Bayes, KNN, Ran…
A controlled study of GPT-2 Small found that representational simplicity and causal circuit size dissociate in a threshold-dependent way, with adversarially trained models needing substantially fewer edges only at high f…
A calibrated hybrid ensemble combining five deep learning models and three classical machine learning models via a logistic regression stacking meta-learner achieved 74.2% seizure-level sensitivity at 1.24 false alarms p…