long short-term memory
PulseAugur coverage of long short-term memory — every cluster mentioning long short-term memory across labs, papers, and developer communities, ranked by signal.
- developed by Recurrent Neural Networks 90%
- instance of BiLSTM 90%
- instance of Bi-LSTM-AMSM: bidirectional long short-term memory network and attention mechanism with semantic mining for e-commerce web page recommendation 90%
- competes with Mass-Conserving Perceptron 75%
- instance of DagsHub 70%
- used by Gotit.pub 70%
- used by ScienceCast 70%
- competes with random forest 70%
- used by alphaXiv 70%
- instance of gated recurrent unit 70%
- used by multilayer perceptron 70%
- used by CatalyzeX 70%
- 2026-05-14 research_milestone A hybrid LSTM model achieved the lowest final displacement error in dynamic movement forecasting. source
13 day(s) with sentiment data
-
Flow Matching Model Predicts Aircraft Trajectories with High Accuracy
Researchers have developed FlowATC, a novel architecture for predicting aircraft trajectories using flow matching techniques. Trained on over a million Automatic Dependent Surveillance-Broadcast (ADS-B) trajectory windo…
-
LLMs generate synthetic manufacturing data, outperforming traditional methods
Researchers have developed a new method using Large Language Models (LLMs) to generate synthetic time series data for manufacturing processes. This approach addresses the common challenge of limited labeled data in manu…
-
New HyCoSeq framework uses hyperbolic geometry for genomic sequence learning
Researchers have developed HyCoSeq, a new framework for learning representations of genomic sequences using hyperbolic geometry. This approach incorporates weighted Lorentzian residual aggregation and a bidirectional lo…
-
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 AI system uses audio to track hidden vehicles
Researchers have developed a novel two-stage system for detecting and tracking hidden dynamic objects using audio representations. The first stage involves self-supervised pre-training on raw audio waveforms, inspired b…
-
Time Series Analysis and Forecasting Series Explores Models and Applications
This three-part series delves into time series analysis and forecasting, covering fundamentals, data preparation with Pandas, and various forecasting models. Part 3 focuses on modeling, exploring techniques like ARIMA, …
-
New neural framework Prism-SQA enhances sEMG signal quality assessment
Researchers have developed Prism-SQA, a novel neural framework designed to improve the assessment of surface electromyography (sEMG) signal quality. Unlike existing black-box methods, Prism-SQA offers interpretability b…
-
VertiFuseX: New LSTM Architecture Boosts Financial Forecasting Accuracy
Researchers have developed VertiFuseX, a novel deep learning architecture designed for more generalizable financial forecasting. This hybrid LSTM model utilizes a unique penultimate-layer vertical fusion of multi-scale …
-
Patient survey data boosts opioid use disorder prediction accuracy
A new study published on arXiv demonstrates that incorporating patient-reported survey data significantly enhances the prediction of opioid use disorder (OUD) when combined with electronic health records (EHRs). Researc…
-
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…
-
Neuromorphic Battery Management System for eVTOL Aircraft Developed
Researchers have developed nBMS, a neuromorphic battery management system designed for eVTOL aircraft. This system utilizes a spiking state-of-charge core with a low-power, event-driven design, achieving an RMSE of 2.45…
-
Foundation models require fine-tuning for diabetes glucose forecasting
A new study published on arXiv evaluates the effectiveness of time-series foundation models for continuous glucose monitoring (CGM) forecasting, particularly for individuals with type 1 and type 2 diabetes. The research…
-
Deep Learning Approach Enhances Motor Fault Diagnosis with Sensor Fusion
This research paper introduces a novel deep learning approach for diagnosing faults in bearings and induction motors by fusing data from multiple sensors. The study utilizes Convolutional Neural Networks (CNNs) to analy…
-
Nyström attention matches full attention for stock prediction
Researchers have developed a novel approach called Nyström attention that matches the performance of full attention mechanisms in cross-sectional stock prediction tasks. This new method, which decomposes the inter-stock…
-
New Riemannian Language Models achieve 2x perplexity improvement
Researchers have introduced Riemannian Language Models (RiLM), a novel approach to parameter-efficient language modeling that eliminates the need for an output matrix. This method leverages geodesic decoding, where cont…
-
New SIDE method detects sensor impersonation in IoT devices
Researchers have developed a novel method called SIDE for detecting sensor impersonation in Internet of Things (IoT) devices. This approach treats detection as a sequence prediction problem, utilizing a lightweight mode…
-
New RL Policy Slashes Design Rule Violations by 92% in Chip Routing
Researchers have developed a history-aware offline reinforcement learning policy to address routing bottlenecks in physical design, particularly for complex, dense layouts. This new policy utilizes a lightweight LSTM ar…
-
New Quantum Recurrent Unit Offers Enhanced Scalability and Efficiency
Researchers have developed a new Quantum Prototypical Recurrent Unit (QPRU) that is more parameter-efficient than existing classical and quantum recurrent architectures. This QPRU demonstrates competitive forecasting pe…
-
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 Unified Particle Filter LSTM Enhances Process Simulation
Researchers have developed a novel Unified Particle Filter LSTM (Unified PF-LSTM) designed for data-driven process simulation. This model addresses limitations in standard recurrent neural networks by maintaining and up…