33 stories tagged with #neural-networks, in publish-time order across the WeSearch catalog. Tag pages update as new stories ingest.
⌘ RSS feed for this tag → or search "Neural Networks"
Neuro-Symbolic Verification of LLM Outputs for Data-Sensitive Domains (extended preprint)
LLMs deployed in high-stakes domains face fundamental reliability challenges: hallucinations, inconsistencies, and privacy vulnerabilities introduce unacceptable risks where errors…
What will you think of when you read about a neural network!!? Mathematics? 🤔
The Math Behind Neural Networks — Explained Like Nobody Did for Me 🧨 ...…
In Search of the Ingredients of Open-Endedness: Replicating Picbreeder with Large Vision-Language Models
We are in the midst of large-scale industrial and academic efforts to automate the processes of scientific, technological and creative production through AI-driven assistants. Hist…
Boosting Inference with Guided Reasoning: Stochastic Exploration for Recursive Models
Recent work on recursive architectures has shown that tiny neural networks can be surprisingly powerful on structured reasoning tasks. The trick is to model reasoning trajectories …
Online Hand Gesture Recognition Using 3D Convolutional Neural Networks
In human computer interaction, real-time detection and classification of dynamic hand gestures is challenging as: 1) the system must run in a real-time video stream and there is no…
The Math Behind Neural Networks — Explained Like Nobody Did for Me 🧨
How does a neural network actually learn to be less wrong? Not the hand-wavy version. The real one....…
Debiasing Graph Neural Networks for Recommendation with Causal RL
How to use Inverse Propensity Scoring and Causal Embeddings to fix popularity bias in GNN recommender systems.…
High Quality Embeddings for Horn Logic Reasoning
Neural networks can be trained to rank the choices made by logical reasoners, resulting in more efficient searches for answers. A key step in this process is creating useful embedd…
Closed-form predictive coding via hierarchical Gaussian filters
Predictive coding (PC) offers a local and biologically grounded alternative to backpropagation in the training of artificial neural networks, yet to date, it remains slower, and pe…
Representability-Aware Neural Networks for Reduced Density Matrices: Application to Fractional Chern Insulators
We develop a representability-aware and interpolable neural network (NN) framework for predicting two-particle reduced density matrices (2-RDMs). The NN incorporates a subset of re…
Machine-Learning-Enhanced Non-Invasive Testing for MASLD Fibrosis: Shallow-Deep Neural Networks Versus FIB-4, Tabular Foundation Models, and Large Language Models
Advanced fibrosis is a major determinant of liver-related morbidity in metabolic dysfunction-associated steatotic liver disease (MASLD). FIB-4 is widely used as a first-line non-in…
Collocational bootstrapping: A hypothesis about the learning of subject-verb agreement in humans and neural networks
In what ways might statistical signals in linguistic input assist with the acquisition of syntax? Here we hypothesize a mechanism called collocational bootstrapping, in which regul…
Axiomatizing Neural Networks via Pursuit of Subspaces
While deep neural networks have achieved remarkable success across a wide range of domains, their underlying mechanisms remain poorly understood, and they are often regarded as bla…
The Devil is in the Condition Numbers: Why is GLU Better than non-GLU Structure?
Gated Linear Units (GLU) and their variants are widely adopted in modern open-source large language model architectures and consistently outperform their non-gated counterparts, ye…
ELSA: An ELastic SNN Inference Architecture for Efficient Neuromorphic Computing
Spiking neural networks (SNNs) exploit event-driven and addition-only computation to substantially improve efficiency for intelligent computation. A key temporal property of SNNs, …
I ran MNIST on an ESP32-C3 without TensorFlow, TFLite, or any ML runtime
I ran MNIST digit recognition on an ESP32-C3 — without TensorFlow, TFLite, or any ML runtime. The...…
Generative Recursive Reasoning
How should future neural reasoning systems implement extended computation? Recursive Reasoning Models (RRMs) offer a promising alternative to autoregressive sequence extension by p…
Robust Basis Spline Decoupling for the Compression of Transformer Models
Decoupling is a powerful modeling paradigm for representing multivariate functions as compositions of linear transformations and univariate nonlinear functions. A single-layer deco…
Adaptive Multi-Scale Goodness Aggregation for Forward-Forward Learning
We propose Adaptive Multi-Scale Goodness Aggregation (AMSGA), a novel extension of the Forward-Forward (FF) algorithm designed to improve stability, robustness, and generalization …
The cut in the Mixture of Experts compute graph
LeetCode for Machine Learning. Practice ML coding problems with a real Python execution environment.…
NeuroMAS: Multi-Agent Systems as Neural Networks with Joint Reinforcement Learning
Multi-agent language systems are often built as hand-designed workflows, where agents are assigned semantic roles and communication protocols are specified in advance. We propose N…
Virtual Nodes Guided Dynamic Graph Neural Network for Brain Tumor Segmentation with Missing Modalities
Multimodal magnetic resonance imaging (MRI) is crucial for brain tumor segmentation, with many methods leveraging its four key modalities to capture complementary information for e…
Surface-Form Neural Sparse Retrieval: Robust Fuzzy Matching for Industrial Music Search
Music search at the scale of Amazon Music presents a unique challenge: queries frequently deviate from indexed metadata due to misspellings, transpositions, and phonetic variations…
A Geometric Calculator Inside a Neural Network
We found a neural mechanism that operates over manifolds: a general-purpose addition module inside Llama 3.1 8B which manipulates circular representations of numbers.…
Agentic Discovery of Neural Architectures: AIRA-Compose and AIRA-Design
Toward recursive self-improvement, we investigate LLM agents autonomously designing foundation models beyond standard Transformers. We introduce a dual-framework approach: AIRA-Com…
Diagonal Adaptive Non-local Observables on Quantum Neural Networks
Adaptive Non-local Observables (ANOs) have shown that making quantum observables dynamic can substantially enlarge the function space of Variational Quantum Algorithms, partly shif…
Shapley Neuron Values for Continual Learning: Which Neurons Matter Most?
Continual learning enables neural networks to learn tasks sequentially without forgetting previously acquired knowledge. However, neural networks suffer from catastrophic forgettin…
Softmax in front of CrossEntropyLoss: 16 other bugs PyTorch won't catch
A walkthrough of the 17-rule design-time linter inside Neurarch: what each rule catches, why it matters, and where static analysis stops being useful for neural networks.…
When Chaos Wins: Adding Noise Improved My Snake AI's Stability
Greetings all! Continuing the series where I build Rainbow DQN one component at a time on Snake. The...…
Achieving last-iterate convergence in a QNN via an autonomous Gmetric driver
psi.emergence contains the master source code for the NB (No Boundary Gate) Quantum-Inspired Neural Network framework, utilizing continuous phase memory to demonstrate emergent int…
Understanding Reinforcement Learning with Neural Networks Part 6: Completing the Reinforcement Learning Process
In the previous article we covered the basics of training, and how rewards, derivatives and step-size...…
A Single Neuron Is Sufficient to Bypass Safety Alignment in LLMs
Safety alignment in language models operates through two mechanistically distinct systems: refusal neurons that gate whether harmful knowledge is expressed, and concept neurons tha…