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.
1 day(s) with sentiment data
-
Time series forecasting explained with Zillow's $9B lesson
This article explains time series forecasting, a crucial but often complex aspect of data analysis. It uses the example of Zillow's costly failure in iBuying to illustrate the dangers of models that don't account for ch…
-
LSTM networks overcome RNN memory limitations with gating mechanisms
The Long Short-Term Memory (LSTM) network was developed to address the limitations of traditional Recurrent Neural Networks (RNNs) in handling sequential data. Vanilla RNNs struggle with remembering information over lon…
-
CatNet paper introduces SHAP for feature importance in LSTM FDR control
Researchers have introduced CatNet, a novel algorithm designed to control the False Discovery Rate (FDR) and identify significant features within Long Short-Term Memory (LSTM) networks. This method utilizes the derivati…
-
Neural-Actuarial Longevity Forecasting: Anchoring LSTMs for Explainable Risk Management
Researchers have developed a new neural-actuarial framework called Hybrid-Lift to improve longevity forecasting. This approach combines Hierarchical LSTM networks with a Mean-Bias Correction anchoring mechanism to addre…
-
Towards AI explains fundamentals of time series analysis before model application
This guide explains the fundamental differences between standard machine learning data and time series data, emphasizing that the order of observations is crucial in time series. It details various types of time series …
-
Auto-encoders and PCA accelerate phase-field simulations with 80% accuracy
Researchers have developed a data-driven framework using auto-encoder neural networks and principal component analysis to significantly reduce the dimensionality of simulated microstructural images, achieving a reductio…
-
AI governance framework integrates US banking regulations for fraud detection
Researchers have developed a new framework to help U.S. financial institutions navigate the complex regulatory landscape for AI-driven fraud detection. This framework, called RGF-AFFD, integrates requirements from four …
-
Geometric Evolution Graph Convolutional Networks enhance graph representation learning
Researchers have developed a new framework called the Geometric Evolution Graph Convolutional Network (GEGCN) to improve graph representation learning. This novel approach utilizes a Long Short-Term Memory (LSTM) networ…
-
Hybrid quantum-classical model enhances financial volatility forecasting
Researchers have developed a hybrid quantum-classical framework for financial volatility forecasting, integrating a Long Short-Term Memory (LSTM) network with a Quantum Circuit Born Machine (QCBM). The LSTM extracts tem…
-
LLMs and normalizing flows tackle incomplete healthcare data for treatment effect estimation
Researchers have developed a novel two-stage pipeline, CausalFlow-T, designed to improve treatment effect estimation from incomplete longitudinal electronic health records. The first stage utilizes a DAG-constrained nor…
-
AI models forecast oncology demand and vineyard disease risk
Two new research papers explore advanced time-series forecasting methods for distinct domains. One paper introduces an event-based approach for predicting vineyard disease risk, utilizing environmental data and comparin…
-
Paper on wireless sensor network fault identification withdrawn
This paper introduces HiFiNet, a novel hierarchical framework for identifying faults in Wireless Sensor Networks (WSNs). The system uses edge classifiers with LSTM autoencoders for temporal feature extraction and initia…
-
Traditional ML models outperform deep learning for tweet and email sentiment analysis
A recent study compared traditional machine learning models with deep learning architectures for sentiment analysis on social media and email data. For tweet sentiment classification, a Logistic Regression model using T…
-
New study benchmarks machine transliteration models for Tajik-Farsi languages
This paper introduces a new benchmark for machine transliteration between Tajik and Farsi, developing a unique parallel corpus from diverse sources. The study compares six model architectures, including rule-based syste…
-
Researchers develop stable, explainable AI for elderly fall detection
Researchers have developed a new framework for skeleton-based fall detection that uses a temporally stabilized attribution mechanism called T-SHAP. This method enhances the interpretability of AI models used in elderly …
-
LSTM deep learning model outperforms ML for Mobile Legends app review sentiment analysis
This paper evaluates machine learning and LSTM-based deep learning models for sentiment analysis of Mobile Legends app reviews. Utilizing a dataset of 10,000 labeled reviews, the study found that the LSTM model achieved…
-
Recurrent RL improves chemotherapy control under partial patient observability
Researchers have developed a recurrent deep reinforcement learning approach to optimize chemotherapy dosing under conditions where a patient's full state is not observable. By using memory-augmented policies with LSTM a…
-
Researchers develop AI framework for fluid-structure interaction prediction
Researchers have developed a new machine learning framework for predicting fluid-structure interactions (FSI) over long periods on deforming meshes. The system integrates a graph neural operator with a vision Transforme…
-
AI routing framework boosts LEO satellite network performance and efficiency
Researchers have developed a novel spatial-temporal learning-based distributed routing framework designed for dynamic Low Earth Orbit (LEO) satellite networks. This framework integrates Graph Attention Networks (GAT) an…
-
Deep Reinforcement Learning Optimizes Data Center Energy Use
This paper introduces a new Deep Reinforcement Learning (DRL) framework to manage energy consumption in data centers. The system dynamically coordinates solar, wind, battery storage, and grid power to reduce costs and c…