Neural Networks news and analysis on Web Pulse: 1654 curated articles tracking the latest Neural Networks developments, tools, and research, updated continuously from vetted sources.
Developer thevoxium released bare-lm, a minimal autograd tensor library written in C, installable via a git clone and make build or prebuilt Linux and macOS tarballs. The library provides a Memory object with 256 MB perm…
A new arXiv paper, arXiv:2609.22129v1, presents Helix-FNO, a teacher-student architecture that couples a thirty-two-state mechanistic teacher with a Fourier neural operator (FNO) student to learn solution operators in th…
Researchers introduced Unsupervised Graph Collective Anomaly Detection (UGCAD), a framework that uses a variational graph autoencoder (VGAE) to learn graph representations and enhance clustering for identifying collectiv…
A hybrid vision architecture combining frame-based and event-based cameras achieves segmentation rates up to 500 Hz at under 1.87 mJ per inference, according to an arXiv paper (arXiv:2609.22500v1). The system pairs a 42k…
Researchers proposed MFP, a reaction yield prediction method built on role-aware Morgan fingerprints that aggregates count-based circular fingerprints by chemical role (reactant, reagent, product) and combines them with …
Self-supervised pretraining on 3D CTA scans reduced modality imbalance and improved cross-modal integration for multimodal stroke recurrence prediction, according to an arXiv paper (arXiv:2609.22271v1) whose code is publ…
A single-subject EEG-to-image baseline on the THINGS-EEG2 dataset achieved image recall of 12.83 +/- 0.58%, 39.17 +/- 1.76%, and 58.00 +/- 1.73% at ranks 1, 5, and 10 across three training seeds, against analytical chanc…
A blog post titled "Lean Verified Transformers" presents a Lean formalization of foundational Transformer properties — including tensor parallelism, data parallelism, batch invariance, permutation invariance, tiling corr…
Capsize Games released SpikeForge 0.4.0 and 0.5.0, splitting its Python spiking-neural-network toolkit into four separately shipped packages: the core spikeforge training workflow, spikeforge-targets conversions, the off…
The Transformer neural network architecture, introduced in the 2017 paper "Attention is All You Need," has become the go-to deep learning architecture for text-generative models including OpenAI's GPT, Meta's Llama, and …
James Hurley gave a talk on real-time video upscaling using convolutional neural networks and WebGPU. The presentation focused on performance considerations for running CNN-based upscaling in the browser.
A study published in Science Bulletin led by Dr. Zheng Sun of Baylor College of Medicine and Dr. Yanlin He of LSU's Pennington Biomedical Research Center traced pregnancy-related memory lapses to a hypothalamus-to-hippoc…
Maths educator Grant Sanderson of 3Blue1Brown has launched a series framing intelligence as compression, arguing that distilling fundamental structure from the real world and relating it usefully to other things is what …
A developer built a ~10.6 million parameter decoder-only Transformer from scratch in PyTorch and trained it end-to-end on the Tiny Shakespeare dataset using only the free tier of Google Colab's T4 GPU. The 6-layer, 6-hea…
A three-stage parameter-efficient framework adapting DINOv3 Vision Transformer models to synthetic aperture sonar (SAS) automatic target recognition found that Low-Rank Adaptation (LoRA) alone raised area under the preci…
Researchers introduced Bio-MF, a latent-free one-step MeanFlow framework for EEG-conditioned fNIRS generation, detailed in arXiv paper 2609.20904v1. On Dataset 1, EEG plus synthetic fNIRS improved accuracy over EEG-only …
Researchers introduced FedDCN, a generalization of Deep Clustering Networks to the federated scenario, detailed in arXiv paper 2609.21829v1. FedDCN simultaneously optimizes a reconstruction loss and a clustering loss, ge…
Neural Cellular Automata (NCAs) outperform comparable recurrent and feed-forward architectures on few-shot and scale-variant MNIST benchmarks with a parameter budget of roughly 9,800 parameters, according to a paper publ…
A new neural network model for identifying text content file types, especially source code, is approximately four times faster than Google's Magika and 28% smaller in size, according to an arXiv paper (2609.21306v1). The…
A progressive transformer-based framework for fresco-fragment style classification improved accuracy from 0.604 to 0.656 and macro-F1 from 0.596 to 0.648 on the CLEOPATRA dataset over a standard ViT-B/16 baseline, accord…