Neural Networks news and analysis on Web Pulse: 1259 curated articles tracking the latest Neural Networks developments, tools, and research, updated continuously from vetted sources.
An analysis of Adolescent Brain and Cognitive Development Study data found that children with ADHD showed reduced glial cellularity in 20 white matter tracts at age 9 and reduced axonal organization in 16 tracts between …
Kimi K3, an AI model from Moonshot AI, introduces Attention Residuals, replacing standard uniform residual connections in deep transformers with attention-weighted layer outputs, allowing the model to dynamically weight …
A study published in Nature, led by Devon Stoliker from Monash School of Psychological Sciences, found that individual brain patterns during psychedelic trips show hidden order rather than the chaos seen in group average…
ICONIP 2026, a major conference on neural networks and intelligent systems, may pull a sole author's paper from the proceedings if the author skips the in-person presentation without arranging a substitute. Organizers ty…
Researchers propose RoBell-RVFL, a robust generalized bell random vector functional link network that uses a dual-strategy, sample-level weighting mechanism to handle class imbalance and label noise, preserving minority …
A developer created a multilayer perceptron (MLP) from scratch, manually computing all forward and backward passes with a calculator to deepen understanding of neural networks. The project, detailed in a technical blog p…
Denis Shiryaev released DesktopFly on August 18th, an open-source macOS toy that simulates a 3D fruit fly on application windows using a 668-neuron circuit with about 19,000 synaptic connections extracted from the FlyWir…
A new open-source macOS app, DesktopFly, simulates a 3D fruit fly on the desktop using a live spiking simulation of the real FlyWire connectome, with 23,210 neuron soma positions from FlyWire v783 and a 668-neuron circui…
SineKAN, a new variant of Kolmogorov-Arnold Networks (KANs) that replaces B-spline activations with sine functions, may outperform traditional B-splines for certain tasks such as physics-informed neural networks and sign…
Traveling electrical waves sweeping across the brain may serve as a computational engine for perception, memory, and prediction, according to a review by Salk Institute neuroscientists published in Neuron on July 21, 202…
Researchers proposed the Physics Informed Kernel Function Neural Operator (PIKFNO), an interpretable neural operator that incorporates physics-informed kernel functions derived from governing equations, achieving high pr…
A new arXiv study (2608.14636v1) empirically evaluated fractional optimizers and fractal activation functions in neural network training, finding that regularization-style fractional scaling pairs well with selected frac…
A new arXiv preprint (2608.14638v1) introduces local and global edge-of-chaos (EoC) definitions for randomly initialized autoencoders, using random matrix theory spectral techniques and the Sudakov-Fernique inequality to…
Researchers propose BDIP-Net, a graph neural network that explicitly models intra-layer and inter-layer interactions for property prediction of bilayer materials, outperforming existing approaches on the BiDB, HetDB, and…
A new position paper on arXiv (2608.14569v1) argues that neural constraint solvers cannot guarantee correctness under distribution shifts and must integrate symbolic methods to achieve provable correctness. The authors, …
Binary cross entropy is a loss function used in binary classification problems, where the goal is to minimize the difference between predicted probabilities and actual class labels. The article explains why it is preferr…
A new technical explainer on activation functions highlights the vanishing gradient problem that plagues Sigmoid and Tanh in deep networks, and introduces ReLU as a solution. The article includes Python code demonstratin…
Neurable's EEG-powered headphones revealed that a founder's cognitive performance during a 10-day business trip across three countries often contradicted their subjective feelings, with sleep debt repaid but circadian rh…
A new historical strategy game, Kurtuluş 1919, lets players relive the Turkish War of Independence from Mustafa Kemal's landing at Samsun in May 1919 to the last foreign soldier leaving, with the goal of securing the Mis…
Researchers using the CL1 closed-loop electrophysiology platform found that modular cortical cultures of human iPSC-derived neurons significantly outperformed unconstrained monolayers and 3D organoids on a spatio-tempora…