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.
- instance of gated recurrent unit 70%
- competes with gated recurrent unit 70%
- instance of multilayer perceptron 70%
- used by multilayer perceptron 70%
- other gated recurrent unit 70%
- used by graph neural networks 70%
- used by Robert Ślepaczuk 70%
- used by Shap 70%
- developed by xLSTM: Extended Long Short-Term Memory 70%
- used by xLSTM: Extended Long Short-Term Memory 70%
- used by gate 70%
- uses graph attention network 70%
- 2026-05-14 research_milestone A hybrid LSTM model achieved the lowest final displacement error in dynamic movement forecasting. source
19 day(s) with sentiment data
-
AI policies learn cybersecurity penetration testing faster with history aggregation
Researchers have developed and evaluated reinforcement learning policies for penetration testing in cybersecurity scenarios with partial observability. They compared several Proximal Policy Optimization (PPO) variants, …
-
Hybrid CNN-LSTM model boosts cybersecurity for renewable energy grids
Researchers have developed a novel hybrid CNN-LSTM framework designed to enhance cybersecurity in smart renewable energy grids. This model effectively detects both immediate anomalies and gradual, low-and-slow attack ca…
-
New GNN approach enhances multi-site pollution prediction accuracy
Researchers have developed a novel approach using Graph Neural Networks (GNNs) to improve the accuracy of particulate matter (PM) pollution prediction. This method dynamically constructs graphs based on inter-class rela…
-
AI Model Explained: LLM, Transformer, Diffusion, and More
This article explains various types of AI models, differentiating between Dense models and Mixture of Experts (MoE) for Large Language Models (LLMs). It details the Transformer architecture, which is foundational to mod…
-
Topological Neural Dynamics framework shifts sequence modeling to neuron-wise dynamics
A new sequence modeling framework called Topological Neural Dynamics (TND) has been proposed, shifting computation from layer-wise to neuron-wise dynamics. This approach represents a neural system as a directed neuron g…
-
ITNet architecture unifies convolution, attention, and recurrence
Researchers have introduced ITNet, a novel neural network architecture that unifies convolution, attention, and recurrence into a single learnable integral transform. This architecture uses a learnable kernel, implement…
-
Graph Neural Networks enhanced with proximity graphs for dust emission forecasting
Researchers have developed a novel method to enhance Graph Neural Networks (GNNs) for dust source emission forecasting by incorporating proximity graphs. These graphs, including Delaunay triangulation, Gabriel graph, k-…
-
Evolution of Language Models: From Single Neurons to LSTMs
The evolution of language models traces a path from early single neurons in 1958 to more complex architectures like Multilayer Perceptrons (MLP) and Recurrent Neural Networks (RNN). While RNNs introduced sequential proc…
-
New LSTM-ViT Architecture Improves Weather Forecast Error Prediction
Researchers have developed a novel hybrid LSTM-Vision Transformer (LSTM-ViT) architecture to improve the prediction of forecast errors in high-resolution numerical weather prediction (NWP) systems. This new framework in…
-
Mamba and PPO achieve superior safety in spacecraft control
A new research paper explores the effectiveness of various recurrent neural network architectures and reinforcement learning algorithms for adaptive safety-critical control in spacecraft proximity operations. The study …
-
AI algorithm enhances wireless sensor network efficiency
A research paper proposes an enhanced evolutionary multi-objective deep reinforcement learning algorithm to address challenges in wireless rechargeable sensor networks (WRSNs). The algorithm aims to balance node surviva…
-
New GRNGC Framework Enhances Causal Discovery in Complex Industrial Processes
Researchers have developed a new gradient-based causal discovery framework called GRNGC, designed to overcome limitations in existing neural network-based Granger causality models. GRNGC reduces computational costs by u…
-
AI Security Agent for Banking Unveiled in Research Paper
A new research paper details an AI security agent designed for banking, capable of detecting multi-vector fraud and anti-money laundering (AML) activities across both retail and corporate accounts. The agent employs a t…
-
New Self-Supervised GNN Framework Enhances Network Intrusion Detection
Researchers have developed a novel self-supervised Graph Neural Network (GNN) framework for network intrusion detection systems (NIDS). This approach explicitly utilizes real timestamps to capture temporal dependencies,…
-
New method improves electricity load forecasting with deep learning
Researchers have developed a delta-based target reformulation method for short-term electricity load forecasting using deep learning models like LSTMs and Transformers. This approach predicts the change in load between …
-
Machine learning forecasts AMR trends, aids policy with RAG system
A new research paper proposes a machine learning approach to forecast bacterial antimicrobial resistance (AMR) trends using data from the WHO Global Antimicrobial Resistance and Use Surveillance System (GLASS). The stud…
-
New ML-Augmented Hydrology Model Offers Enhanced Interpretability
Researchers have developed a new approach to hydrological modeling that combines machine learning with physically interpretable models. This method, called the Mass-Conserving Perceptron (MCP), aims to improve predictiv…
-
Simple argmax baseline matches LLMs in Next Activity Prediction benchmark
A new paper on arXiv benchmarks the performance of various models for Next Activity Prediction (NAP), a key component of predictive process monitoring. The study compares large language models (LLMs), Transformers, LSTM…
-
Machine learning models predict exam outcomes using physiological signals
Researchers have explored the use of machine learning to predict exam performance by analyzing physiological signals such as heart rate and electrodermal activity. The study employed a range of models, from traditional …
-
Deep learning models achieve 98.91% accuracy in emotion recognition from physiological signals
Researchers have developed a deep learning approach for recognizing emotions from physiological signals, achieving a high accuracy of 98.91%. The study evaluated Long Short-Term Memory (LSTM), Temporal Convolutional Net…