PulseAugur
EN
LIVE 20:22:21
ENTITY gated recurrent unit

gated recurrent unit

PulseAugur coverage of gated recurrent unit — every cluster mentioning gated recurrent unit across labs, papers, and developer communities, ranked by signal.

Show in brief
Total · 30d
19
112 over 90d
Releases · 30d
0
0 over 90d
Papers · 30d
17
106 over 90d
TIER MIX · 90D
TOPICS
RELATIONSHIPS
SENTIMENT · 30D

7 day(s) with sentiment data

RECENT · PAGE 1/6 · 117 TOTAL
  1. TOOL · CL_366228 ·

    Transformer model forecasts criminal court case outcomes

    Researchers have developed a transformer-based time series model to analyze and forecast outcomes within the criminal legal system. This model treats court cases as event sequences, integrating textual data from clerk n…

  2. RESEARCH · CL_366273 ·

    New OCTR2A system forecasts urban agent trajectories using only RGB cameras

    Researchers have developed OCTR2A, a novel architecture for real-time trajectory projection and forecasting of agents at urban intersections using only RGB cameras. This system addresses the limitations of relying on ex…

  3. TOOL · CL_365553 ·

    New DDSL framework improves financial market state labeling

    Researchers have developed DDSL, an iterative self-labeling framework designed to construct labels for financial market states. This framework couples a price- and grammar-guided Viterbi labeler with a Transformer class…

  4. RESEARCH · CL_365554 ·

    New ForceBody dataset integrates force and torque data into parametric body models

    Researchers have introduced ForceBody, a novel dataset designed to integrate ground truth force and torque data into parametric body models for motion generation and reconstruction. This dataset addresses the limitation…

  5. RESEARCH · CL_359520 ·

    Estonia to close Russia border after alleged GRU sabotage attempt

    Estonia announced it will close all its border crossings with Russia starting December 1st. This decision follows an alleged sabotage attempt on a drone factory, which Estonia attributes to Russia's GRU military intelli…

  6. TOOL · CL_327284 ·

    New Bi-Mamba Model Enhances Robot Navigation with Real-Time Trajectory Prediction

    Researchers have developed TrajMamba, a novel bidirectional state space model designed for real-time human trajectory prediction using RGB-D cameras. This model addresses the train-deploy pipeline gap by aligning pose e…

  7. TOOL · CL_324961 ·

    New dataset Ampe-DB highlights generalization challenges in human activity recognition

    Researchers have introduced Ampe-DB, a new multimodal dataset designed to capture human activity and interaction within the context of Ampe, a traditional Ghanaian game. The dataset includes RGB video, pose representati…

  8. TOOL · CL_322783 ·

    DistilGPT-2 recommended for improving TinyGPT project

    The author discusses various Large Language Models (LLMs) suitable for improving a project that previously used a small, custom-trained Transformer model called TinyGPT. They evaluate options like LSTM/GRU, DistilGPT-2/…

  9. TOOL · CL_317388 ·

    New algorithms tackle UAV edge network caching challenges

    Researchers have developed new algorithms for content caching in dynamic multi-unmanned aerial vehicle (UAV) edge networks. The proposed methods, DE-UBAC and GRU-DEPPO, aim to improve cache-hit performance and reduce de…

  10. TOOL · CL_317237 ·

    baseVultra: New compact nonlinear recurrence cell outperforms LSTM/GRU in specific settings

    Researchers have introduced baseVultra, a novel compact nonlinear recurrent neural network cell designed for streaming sequence modeling. This new architecture reallocates computational resources from gate transformatio…

  11. TOOL · CL_312449 ·

    New CVG-SGM method enhances object identity persistence in 4D scene graphs

    Researchers have developed a new method called CVG-SGM to improve the persistence of object identity in 4D scene graphs, particularly when objects become temporarily invisible. This system uses a novel memory mechanism …

  12. RESEARCH · CL_315130 ·

    Chrono Gate Initialization Boosts LSTM/GRU Performance on Long Dependencies

    A new study published on arXiv investigates the effectiveness of gate initialization techniques versus recurrent dropout and zoneout in Long Short-Term Memory (LSTM) and Gated Recurrent Unit (GRU) networks for learning …

  13. TOOL · CL_308119 ·

    Deep learning models show high accuracy in rodent seizure detection

    Researchers have conducted a large-scale empirical study on deep learning models for detecting and grading the severity of seizures in rodents using synchronized video and EEG recordings. The study evaluated ten video a…

  14. TOOL · CL_300827 ·

    New ST-GRU unit simplifies PredRNN-V2 for video prediction

    Researchers have developed a new spatiotemporal Gated Recurrent Unit (ST-GRU) as an alternative to the Spatio-Temporal Long Short-Term Memory (ST-LSTM) unit used in PredRNN-V2. This ST-GRU unit simplifies the recurrent …

  15. TOOL · CL_289606 ·

    AdaptLSTM framework offers efficient online learning for cloud workload forecasting

    Researchers have developed AdaptLSTM, a novel framework for online learning designed to efficiently forecast cloud workloads amidst changing data distributions. This method selectively updates models when drift is detec…

  16. TOOL · CL_284748 ·

    Machine learning models forecast German electricity redispatch needs

    A new research paper explores the use of machine learning models for forecasting German electricity redispatch needs, addressing challenges like data delays and temporal distribution shifts. The study evaluated several …

  17. RESEARCH · CL_284734 ·

    Neuroevolutionary search yields efficient stock prediction models for edge devices

    Researchers have developed a novel neuroevolutionary architecture search method called ONE-NAS for stock return prediction. This method evolves small recurrent networks that can be deployed on edge devices like Raspberr…

  18. COMMENTARY · CL_277431 ·

    Developer shares Hacktoberfest journey and AI projects on Mastodon

    A developer has shared their experience participating in Hacktoberfest, a yearly event that encourages contributions to open-source projects. The developer, Malik Putra from Indonesia, documented their journey and proje…

  19. TOOL · CL_277359 ·

    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…

  20. TOOL · CL_273619 ·

    Robots struggle to transfer learned communication to physical world

    Researchers have investigated the transferability of co-evolved communication protocols from simulated environments to physical robots. In an experiment involving two e-puck mobile robots controlled by a gated recurrent…