recurrent neural network
PulseAugur coverage of recurrent neural network — every cluster mentioning recurrent neural network across labs, papers, and developer communities, ranked by signal.
- instance of gated recurrent unit 90%
- instance of deep learning 90%
- instance of Gotit.pub 90%
- instance of Recurrent Neural Networks 90%
- instance of artificial neural network 90%
- instance of alphaXiv 90%
- instance of ScienceCast 90%
- instance of multilayer perceptron 90%
- developed by long short-term memory 80%
- used by long short-term memory 70%
- instance of long short-term memory 70%
- instance of CNN 70%
4 day(s) with sentiment data
-
Theory suggests noise fundamentally shapes RNN representation learning
A new theoretical paper explores the impact of intrinsic noise on the learning dynamics of linear recurrent neural networks (RNNs). Researchers argue that noise, often considered a nuisance, can fundamentally shape repr…
-
Machine learning models benchmarked for atmospheric seeing forecasting
Researchers have evaluated machine learning models for short-term atmospheric seeing forecasting, aiming to improve astronomical observations and optical communication. The study compared Gaussian Processes (GPs) and a …
-
AI agents trained for prediction market making on Polymarket
Researchers have developed a cooperative multi-agent reinforcement learning system for market making on prediction markets, specifically addressing challenges posed by Polymarket's thin order books. The system reconstru…
-
New DETRNN Module Enhances Object Detection Accuracy
Researchers have developed DETRNN, a novel module designed to enhance object detection in DETR-style models. This plug-and-play component transforms unordered object queries into a competition-aware sequence, leveraging…
-
Stanford offers free online course on LLM fundamentals
Stanford University is offering a free online course, CME 295: Transformers & Large Language Models, taught by Afshine and Shervine Amidi. The course, which has already garnered over 372,000 views on its first lecture, …
-
AI Generates Korean Handwriting Strokes with RNN for Hangul Day
A project has been developed to generate Korean handwriting strokes using a recurrent neural network (RNN). The project, shared on Hacker News and Mastodon, aims to celebrate Happy Hangul Day by showcasing this AI-drive…
-
Deep learning shows promise in longitudinal medical imaging analysis · 1 source tracked
A scoping review of 102 studies published between 2018 and 2025 reveals that deep learning is a promising field for longitudinal medical imaging analysis. The review found that neurological disorders were the most commo…
-
New dataset Chordonomicon offers 666,000 song chord progressions
Researchers have introduced Chordonomicon, a new dataset comprising over 666,000 song-level symbolic chord progressions. This dataset is significantly larger than existing ones and includes annotations for structural pa…
-
WaveHiTS model enhances wind direction forecasting with wavelet and hierarchical methods
A new model called WaveHiTS has been proposed for wind direction forecasting, integrating wavelet transform with a hierarchical time series approach. This method decomposes wind direction into U-V components and uses wa…
-
New XAI Framework Enhances LSTM Efficiency for Channel Estimation
Researchers have developed a new framework called X-RACE to improve the explainability and efficiency of deep learning models, specifically Long Short-Term Memory (LSTM) networks, used for channel estimation in high-mob…
-
New research tackles handwritten character recognition with novel architectures
Two new research papers explore advancements in handwritten character recognition. The first paper introduces a framework combining Sliding Window Path Signature with Linear Recurrent Units (LRU) to achieve high accurac…
-
New modular deep RNN architecture improves learning for complex dynamics
A new modular deep Recurrent Neural Network (RNN) architecture has been developed to simplify the deployment of various RNN designs and automate derivative calculations for gradient-based learning. This modularity enabl…
-
New Graph Neural Network Accurately Predicts Urban PM2.5 Levels
Researchers have developed a novel Spatially Attentive Graph Neural Network (SA-GNN) to predict PM2.5 concentrations in urban environments. This model was tested using a new dataset collected in Surat, Gujarat, India, w…
-
New LRNBA Architecture Offers Neural Network Compression
Researchers have introduced the Linear Reusable Neural Bases Architecture (LRNBA), a new framework designed to address the memory cost bottleneck in large AI models. LRNBA represents network blocks as linear combination…
-
Deep learning model enhances battery State of Health estimation
Researchers have developed a new framework for estimating the State of Health (SOH) in batteries using a hybrid deep learning model. This model combines Convolutional Neural Networks (CNNs) with Bidirectional Long Short…
-
New FAM-LSTM model improves grape berry temperature forecasting
Researchers have developed a novel FAM-LSTM model, integrating a feed-forward attention mechanism with Long Short-Term Memory networks, to accurately forecast grape berry temperature. This model consistently outperforme…
-
New RNN-based framework boosts multi-GPU simulation of 3D multicellular growth
Researchers have developed a new multi-GPU framework designed to significantly improve the scalability of detailed 3D multicellular growth simulations. This framework utilizes recurrent neural networks (RNNs) to dynamic…
-
Scheduled sampling's effectiveness poorly predicted by exposure gap metric
A new analysis of scheduled sampling in sequence prediction models reveals that the "exposure gap" metric, often cited to address exposure bias, provides minimal predictive power regarding the effectiveness of scheduled…
-
WaveVerif uses sound to verify robotic workflows with 80% accuracy
Researchers have developed a novel framework called WaveVerif that utilizes acoustic side-channel analysis (ASCA) to verify robotic workflows. This system analyzes the sounds emitted by robots during movement to determi…
-
Recurrent Neural Network Learning Dynamics Near Bifurcations Analyzed
A new research paper explores the dynamics of learning in recurrent neural networks (RNNs) near critical transition points, known as bifurcations. The study utilizes the global empirical Neural Tangent Kernel (GeNTK) to…