Neural Networks

Researchers introduced AgentNAS, a method that uses a large language model to generate a seed architecture and decompose it into a slotted architecture for conventional neural architecture search, achieving state-of-the-…

Researchers proposed a graph-regularized deep learning framework for EEG-based emotion recognition that models psychological interdependencies between emotion classes, achieving up to +5.42% accuracy improvement and a 39…

Researchers introduced Omni-Sleep, a foundation model for sleep analysis that leverages the physiological hierarchy of the central and autonomic nervous systems to learn structured representations from polysomnography da…

Researchers evaluated state-of-the-art tabular models as encoders in image-tabular multimodal learning for the first time, finding that In-Context Learning models, which require labels to process instances, pose a challe…

Researchers identified failure modes in Hamiltonian Generative Networks that prevent temporal generalization in non-conservative environments, and proposed targeted fixes enabling stable dynamics prediction at variable t…

Researchers introduced Lipschitz Scaling Training (LiST), a method that adjusts the Lipschitz constant of neural networks to achieve out-of-the-box calibration while balancing accuracy and robustness. LiST outperforms ba…

Researchers introduced Meta Neural Cellular Automata (MetaNCA), a framework that learns local rules to self-organize the weights of artificial neural networks without backpropagation. The method generates weights for div…

Researchers introduced the Local Linear Transformer (LLT), a neural operator for learning PDE solution maps that combines linear global attention with local spatial mixing and incorporates coordinate and geometry informa…

Researchers prove a law of robustness for two-layer neural networks with arbitrary weights, showing that fitting noisy data forces the Lipschitz constant to be at least of order √(n/m). The result holds for ReLU networks…

Researchers developed a graph neural network model for real-time hand gesture recognition using surface electromyography (sEMG) signals. The model achieved 99% classification accuracy on data from 8 subjects using a Myob…

An interactive guide demonstrates how Transformer models use attention, embeddings, and positional encoding to predict moves in a fading Tic-Tac-Toe game, making the architecture's inner workings accessible. The article …

A developer visualized the training of a deep neural network on the MNIST dataset using PyTorch. The project displays real-time updates of the input image, hidden layer activations, output probability distribution, and l…

Neuronpedia announced the J-space, a global workspace in AI models revealed by Jacobian lens, and added support for 11 more models. The feature allows users to see hidden reasoning in AI, with pre-fitted J-lenses availab…

Hussein Mahdi published a review of the 2009 paper on graph neural networks, covering their theoretical foundations and core mechanisms. The article explores the history, concepts, and philosophy of GNNs.

A new study published in PNAS finds that human neurons have unique structures with more branches and greater surface area, enabling them to perform complex computations individually. Researchers from Hebrew University us…

Researchers at EPFL and Google Research developed Cells2Pixels, a neural cellular automata model that achieves an 8x resolution boost by treating cells as local neural fields rather than pixels. The method decouples rend…

PLOS Computational Biology published a study on July 9, 2026, deriving a closed-form rule for spiking neurons to control linear dynamical systems by emitting spikes only when they move the system closer to a target. The …

Researchers compared three machine learning models of raindrop formation and found that the simplest model, a polynomial-based SINDy framework, outperformed more complex neural network approaches. The study used autoenco…

Scientists at University College London and École Polytechnique Fédérale de Lausanne found that giving real-time success feedback during motor tasks significantly improves human-machine interface control, especially when…

A developer explores the concept of an internal 'workspace' in large language models, analogous to a reasoning blackboard, which emerges from training rather than being explicitly designed. Experiments show that manipula…