A 499-neuron circuit extracted from MaleCNS v1.0, the Janelia-published CC-BY electron-microscopy reconstruction of a male fruit fly's central nervous system, was run as a reservoir on MNIST in PyTorc…
Researchers propose CG4AI, a column generation framework that builds a convex combination of AI models while enforcing linear constraints on outputs, using a master linear program and pricing subprobl…
Researchers introduced an analytic early stopping rule for neural network training that estimates the optimal stopping time without training, using Rademacher complexity with L1-norm instead of L2-nor…
Researchers at an undisclosed institution found that undervolting GPUs during CNN training improves adversarial robustness while cutting energy use. In tests on MNIST and CIFAR-10 with LeNet, VGG-6, a…
ONNX.css, a new open-source tool, compiles ONNX neural network models into CSS stylesheets, enabling browsers to run inference via the style engine. It demonstrates three models: a LeNet-style CNN for…
A developer proposes an opinionated approach to learning reinforcement learning (RL) for large language models (LLMs) by framing a familiar supervised learning problem, such as MNIST classification, a…
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…
Researchers introduced ELVAE, an evidential learning-based variational autoencoder that assigns each latent coordinate an input-dependent normal-inverse-gamma posterior, enabling explicit latent-locat…
A developer implemented batch normalization, layer normalization, and group normalization from scratch and compared their performance on a simple multi-layer perceptron (MLP) classifying the MNIST dat…
A 15-year-old developer in Germany has released ABSL (Adaptive Bit-Shift Learning) v1.0.0, a 100% integer-only neural network training algorithm written in Rust that achieves 91.1% global accuracy on …
Researchers from Georgia Tech and Apple have shown that applying standard graph algorithms to UMAP's internal k-nearest-neighbor (kNN) graph can enhance data sensemaking, outperforming or complementin…
Researchers propose a loss-aware feature-map pruning framework for convolutional neural networks that uses multi-armed bandits (UCB1 and Thompson Sampling) to identify and remove redundant feature map…
A new Bayesian framework called Neural Atom Prevalence (NAP) achieves state-of-the-art structural sparsity in feedforward neural networks, reducing active nodes to as few as 8% of the original dense a…
Every machine learning model, from linear regression to deep neural networks, rests on linear algebra, calculus, and convex optimization, according to a Stochastic Blog post. The post builds each conc…
NVIDIA TensorRT's IProgressMonitor API lets developers make long-running engine builds observable and cancelable in Python and C++, preventing wasted GPU-hours in agent workflows. The interface provid…
Researchers have introduced SechKAN, a Kolmogorov-Arnold Network architecture using hyperbolic secant functions, which achieves superior performance over MLPs and other KAN variants on benchmark datas…
A new implementation of the Fuzzy-Pattern Tsetlin Machine achieves 37 million MNIST predictions per second at 98% accuracy with 4.7 GB/s throughput on a desktop CPU, and demonstrates the first Tsetlin…
A new study on arXiv (2607.16231v1) evaluates OrthoGrad, a geometric intervention that removes the radial component of weight gradients during optimizer updates, in noisy-label image classification. O…
A new study evaluating variational quantum circuits (VQCs) in diffusion models on MNIST and CIFAR-10 found that quantum cores matched classical Fréchet Inception Distance (FID) scores despite using 4.…
A developer published a Keras-based implementation of the LeNet-5 convolutional neural network architecture, originally proposed by Yann LeCun in 1989 for handwritten digit recognition. The implementa…