Mentions
Extended reach
Total likes
Video views
AI synopsis
The discussions consistently show strong support and interest in LSTM's capabilities, with examples like its use in mangrove ecosystem predictions, speech recognition, and hybrid models for stock forecasting. The tone emphasizes LSTM's versatility and importance, with technical references and personal experiment mentions reflecting active engagement with ongoing research.
Most discussions recognize the significance and effectiveness of LSTM models in various applications, with some posts highlighting its foundational role in deep learning and sequence modeling.
Posts demonstrate high interest through mentions of diverse research areas like environmental forecasting, stock prediction, and natural language processing, showing enthusiasm and curiosity.
Several comments delve into technical details, cite examples like the integration of LSTM with CNNs or quantum models, and share personal experiments, indicating deep engagement.
The discussions suggest that LSTMs are viewed as impactful tools capable of advancing fields such as climate prediction, financial forecasting, and AI system reliability, although few posts directly claim revolutionary change.
Long Short-Term Memory (LSTM) is a special type of Recurrent Neural Network (RNN) in deep learning. Its power comes from a "memory cell" and three "gates" (input, forget, output). These gates allow the network to selectively remember or forget information over long periods, https://t.co/dcyexhVtZh
link
My inner circle
It appears that Rubio has long & short term memory issues.
Paper: StoxLSTM: A Stochastic Extended Long Short-Term Memory Network for Time Series Forecasting ( arxiv.org/abs/2509.01187 )
To-do-list that's too long, short-term memory loss, shopping list or a local social media influencer publicity stunt. Yes, it's a real car and yes, it was covered in Post-it notes - hundreds of them. Local influencer doing a publicity stunt.
In this video, I explain the workings and process of creating a chatbot like ChatGPT using open-source tools. Several models and tools are utilized, including LLM zephyr7bbeta, LlamaCPP, LlamaIndex, and Gradio. Follow…
In this video we introduce recurrent neural networks (RNNs), a crucial concept in machine learning. RNNs enable the processing of sequences of data, making them invaluable for tasks such as language modeling and time…
This video provides an in-depth look at text classification using Python, focusing on techniques such as tokenization and word embeddings. Learn how to apply LSTM models to analyze and classify text data effectively…
This video explores how syntactic surprisal influences reading times by examining studies that reveal the cognitive processing involved. We delve into works that show how anticipatory effects shape our understanding of…
Bitcoin Price Forecasting Based on Hybrid Variational Mode Decomposition and Long Short Term Memory Network
RT @probnstat: Long Short-Term Memory (LSTM) is a special type of Recurrent Neural Network (RNN) in deep learning. Its power comes from a "…
Bitcoin Price Forecasting Based on Hybrid Variational Mode Decomposition and Long Short Term Memory Network
RT @probnstat: Long Short-Term Memory (LSTM) is a special type of Recurrent Neural Network (RNN) in deep learning. Its power comes from a "…
RT @probnstat: Long Short-Term Memory (LSTM) is a special type of Recurrent Neural Network (RNN) in deep learning. Its power comes from a "…
RT @probnstat: Long Short-Term Memory (LSTM) is a special type of Recurrent Neural Network (RNN) in deep learning. Its power comes from a "…
RT @TheTuringPost: A must-read paper → Fundamentals of Building Autonomous LLM Agents Reviews the core cognitive subsystems that make up a…
RT @probnstat: Long Short-Term Memory (LSTM) is a special type of Recurrent Neural Network (RNN) in deep learning. Its power comes from a "…
RT @probnstat: Long Short-Term Memory (LSTM) is a special type of Recurrent Neural Network (RNN) in deep learning. Its power comes from a "…
https://t.co/7hntKoWI1c
RT @probnstat: Long Short-Term Memory (LSTM) is a special type of Recurrent Neural Network (RNN) in deep learning. Its power comes from a "…
RT @probnstat: Long Short-Term Memory (LSTM) is a special type of Recurrent Neural Network (RNN) in deep learning. Its power comes from a "…
RT @probnstat: Long Short-Term Memory (LSTM) is a special type of Recurrent Neural Network (RNN) in deep learning. Its power comes from a "…
RT @probnstat: Long Short-Term Memory (LSTM) is a special type of Recurrent Neural Network (RNN) in deep learning. Its power comes from a "…
RT @probnstat: Long Short-Term Memory (LSTM) is a special type of Recurrent Neural Network (RNN) in deep learning. Its power comes from a "…
RT @probnstat: Long Short-Term Memory (LSTM) is a special type of Recurrent Neural Network (RNN) in deep learning. Its power comes from a "…
RT @TheTuringPost: A must-read paper → Fundamentals of Building Autonomous LLM Agents Reviews the core cognitive subsystems that make up a…
Long Short-Term Memory (LSTM) is a special type of Recurrent Neural Network (RNN) in deep learning. Its power comes from a "memory cell" and three "gates" (input, forget, output). These gates allow the network to selectively remember or forget information over long periods, https://t.co/dcyexhVtZh
LSTM ( Long Short Term Memory ) RNN ( Recurrent Neural Model ) Architecture https://t.co/X81t6wa096
New Research: Empirical verification of a transformer voiceprint fault diagnosis method based on convolutional neutral network-long-short term memory and Mel gammatone cepstral coefficient features https://t.co/ZbUrvqW3Li #FrontiersIn #MechanicalEngineering
The model uses a long short-term memory (LSTM) recurrent neural network to predict the gamma passing rate (GPR) for individual stereotactic arcs, classifying them as Ideal (≥95%), Investigate [85%-95%), or Replan (<85%).
Editor’s Featured Papers Volume 340 (Europe) Paper Title: Enhancing the Structural Health Monitoring (SHM) through data reconstruction: Integrating 1D convolutional neural networks (1DCNN) with bidirectional long short-term memory networks (Bi-LSTM) https://t.co/TTA2fbzRl1 https://t.co/UBXb6jpzWw
https://t.co/7hntKoWabE
RT @TheTuringPost: A must-read paper → Fundamentals of Building Autonomous LLM Agents Reviews the core cognitive subsystems that make up a…
RT @TheTuringPost: A must-read paper → Fundamentals of Building Autonomous LLM Agents Reviews the core cognitive subsystems that make up a…
RT @TheTuringPost: A must-read paper → Fundamentals of Building Autonomous LLM Agents Reviews the core cognitive subsystems that make up a…
RT @TheTuringPost: A must-read paper → Fundamentals of Building Autonomous LLM Agents Reviews the core cognitive subsystems that make up a…
RT @TheTuringPost: A must-read paper → Fundamentals of Building Autonomous LLM Agents Reviews the core cognitive subsystems that make up a…
Bitcoin Price Forecasting Based on Hybrid Variational Mode Decomposition and Long Short Term Memory Network
RT @TheTuringPost: A must-read paper → Fundamentals of Building Autonomous LLM Agents Reviews the core cognitive subsystems that make up a…
RT @TheTuringPost: A must-read paper → Fundamentals of Building Autonomous LLM Agents Reviews the core cognitive subsystems that make up a…
RT @TheTuringPost: A must-read paper → Fundamentals of Building Autonomous LLM Agents Reviews the core cognitive subsystems that make up a…
RT @TheTuringPost: A must-read paper → Fundamentals of Building Autonomous LLM Agents Reviews the core cognitive subsystems that make up a…
RT @TheTuringPost: A must-read paper → Fundamentals of Building Autonomous LLM Agents Reviews the core cognitive subsystems that make up a…
RT @TheTuringPost: A must-read paper → Fundamentals of Building Autonomous LLM Agents Reviews the core cognitive subsystems that make up a…
RT @TheTuringPost: A must-read paper → Fundamentals of Building Autonomous LLM Agents Reviews the core cognitive subsystems that make up a…
RT @TheTuringPost: A must-read paper → Fundamentals of Building Autonomous LLM Agents Reviews the core cognitive subsystems that make up a…
RT @TheTuringPost: A must-read paper → Fundamentals of Building Autonomous LLM Agents Reviews the core cognitive subsystems that make up a…
RT @TheTuringPost: A must-read paper → Fundamentals of Building Autonomous LLM Agents Reviews the core cognitive subsystems that make up a…
RT @TheTuringPost: A must-read paper → Fundamentals of Building Autonomous LLM Agents Reviews the core cognitive subsystems that make up a…
Dynamic Sign Language Recognition in Bahasa using MediaPipe, Long Short-Term Memory, and Convolutional Neural Network #Research #Publication #ConvolutionalNeuralNetwork #CNN #LongShortTermMemory #LSTM #MediaPipe #SignLanguage #UNAIR #LPJPHKI https://t.co/YezpbEyZm1
RT @TheTuringPost: A must-read paper → Fundamentals of Building Autonomous LLM Agents Reviews the core cognitive subsystems that make up a…
RT @TheTuringPost: A must-read paper → Fundamentals of Building Autonomous LLM Agents Reviews the core cognitive subsystems that make up a…
RT @TheTuringPost: A must-read paper → Fundamentals of Building Autonomous LLM Agents Reviews the core cognitive subsystems that make up a…
RT @TheTuringPost: A must-read paper → Fundamentals of Building Autonomous LLM Agents Reviews the core cognitive subsystems that make up a…
RT @TheTuringPost: A must-read paper → Fundamentals of Building Autonomous LLM Agents Reviews the core cognitive subsystems that make up a…
RT @TheTuringPost: A must-read paper → Fundamentals of Building Autonomous LLM Agents Reviews the core cognitive subsystems that make up a…
RT @TheTuringPost: A must-read paper → Fundamentals of Building Autonomous LLM Agents Reviews the core cognitive subsystems that make up a…
RT @TheTuringPost: A must-read paper → Fundamentals of Building Autonomous LLM Agents Reviews the core cognitive subsystems that make up a…
RT @TheTuringPost: A must-read paper → Fundamentals of Building Autonomous LLM Agents Reviews the core cognitive subsystems that make up a…
RT @TheTuringPost: A must-read paper → Fundamentals of Building Autonomous LLM Agents Reviews the core cognitive subsystems that make up a…
RT @TheTuringPost: A must-read paper → Fundamentals of Building Autonomous LLM Agents Reviews the core cognitive subsystems that make up a…
RT @TheTuringPost: A must-read paper → Fundamentals of Building Autonomous LLM Agents Reviews the core cognitive subsystems that make up a…
RT @TheTuringPost: A must-read paper → Fundamentals of Building Autonomous LLM Agents Reviews the core cognitive subsystems that make up a…
RT @TheTuringPost: A must-read paper → Fundamentals of Building Autonomous LLM Agents Reviews the core cognitive subsystems that make up a…
RT @TheTuringPost: A must-read paper → Fundamentals of Building Autonomous LLM Agents Reviews the core cognitive subsystems that make up a…
RT @TheTuringPost: A must-read paper → Fundamentals of Building Autonomous LLM Agents Reviews the core cognitive subsystems that make up a…
RT @TheTuringPost: A must-read paper → Fundamentals of Building Autonomous LLM Agents Reviews the core cognitive subsystems that make up a…
RT @TheTuringPost: A must-read paper → Fundamentals of Building Autonomous LLM Agents Reviews the core cognitive subsystems that make up a…
RT @TheTuringPost: A must-read paper → Fundamentals of Building Autonomous LLM Agents Reviews the core cognitive subsystems that make up a…
RT @TheTuringPost: A must-read paper → Fundamentals of Building Autonomous LLM Agents Reviews the core cognitive subsystems that make up a…
RT @TheTuringPost: A must-read paper → Fundamentals of Building Autonomous LLM Agents Reviews the core cognitive subsystems that make up a…
RT @TheTuringPost: A must-read paper → Fundamentals of Building Autonomous LLM Agents Reviews the core cognitive subsystems that make up a…
RT @TheTuringPost: A must-read paper → Fundamentals of Building Autonomous LLM Agents Reviews the core cognitive subsystems that make up a…
RT @TheTuringPost: A must-read paper → Fundamentals of Building Autonomous LLM Agents Reviews the core cognitive subsystems that make up a…
RT @TheTuringPost: A must-read paper → Fundamentals of Building Autonomous LLM Agents Reviews the core cognitive subsystems that make up a…
@yacineMTB @JsnVem LSTMs (Long Short Term Memory) are a good start. Its a type of recurrent neural network which are great for time series data. They are pretty standard for audio classification. Here's some code that can classify urban sounds. https://t.co/61RU3LY8ct Tutorial for doing this on
RT @TheTuringPost: A must-read paper → Fundamentals of Building Autonomous LLM Agents Reviews the core cognitive subsystems that make up a…
RT @TheTuringPost: A must-read paper → Fundamentals of Building Autonomous LLM Agents Reviews the core cognitive subsystems that make up a…
RT @TheTuringPost: A must-read paper → Fundamentals of Building Autonomous LLM Agents Reviews the core cognitive subsystems that make up a…
RT @TheTuringPost: A must-read paper → Fundamentals of Building Autonomous LLM Agents Reviews the core cognitive subsystems that make up a…
RT @TheTuringPost: A must-read paper → Fundamentals of Building Autonomous LLM Agents Reviews the core cognitive subsystems that make up a…
RT @TheTuringPost: A must-read paper → Fundamentals of Building Autonomous LLM Agents Reviews the core cognitive subsystems that make up a…
RT @TheTuringPost: A must-read paper → Fundamentals of Building Autonomous LLM Agents Reviews the core cognitive subsystems that make up a…
RT @TheTuringPost: A must-read paper → Fundamentals of Building Autonomous LLM Agents Reviews the core cognitive subsystems that make up a…
RT @TheTuringPost: A must-read paper → Fundamentals of Building Autonomous LLM Agents Reviews the core cognitive subsystems that make up a…
RT @TheTuringPost: A must-read paper → Fundamentals of Building Autonomous LLM Agents Reviews the core cognitive subsystems that make up a…
RT @TheTuringPost: A must-read paper → Fundamentals of Building Autonomous LLM Agents Reviews the core cognitive subsystems that make up a…
RT @TheTuringPost: A must-read paper → Fundamentals of Building Autonomous LLM Agents Reviews the core cognitive subsystems that make up a…
#52 Membantu pembuatan proposal skripsi Algoritma Long Short Term Memory (LTM) untuk prediksi harga saham #zonauang #jokiit #jokiwebsite #jokiskirpsi #lstm #jokiflutter #jasajoki #jasawebsite #jasaflutter #jokiandroid #portofolio #laravel #flutter https://t.co/5di7aTozXW
RT @TheTuringPost: A must-read paper → Fundamentals of Building Autonomous LLM Agents Reviews the core cognitive subsystems that make up a…
RT @TheTuringPost: A must-read paper → Fundamentals of Building Autonomous LLM Agents Reviews the core cognitive subsystems that make up a…
RT @TheTuringPost: A must-read paper → Fundamentals of Building Autonomous LLM Agents Reviews the core cognitive subsystems that make up a…
RT @TheTuringPost: A must-read paper → Fundamentals of Building Autonomous LLM Agents Reviews the core cognitive subsystems that make up a…
RT @TheTuringPost: A must-read paper → Fundamentals of Building Autonomous LLM Agents Reviews the core cognitive subsystems that make up a…
RT @TheTuringPost: A must-read paper → Fundamentals of Building Autonomous LLM Agents Reviews the core cognitive subsystems that make up a…
RT @TheTuringPost: A must-read paper → Fundamentals of Building Autonomous LLM Agents Reviews the core cognitive subsystems that make up a…
RT @TheTuringPost: A must-read paper → Fundamentals of Building Autonomous LLM Agents Reviews the core cognitive subsystems that make up a…
RT @TheTuringPost: A must-read paper → Fundamentals of Building Autonomous LLM Agents Reviews the core cognitive subsystems that make up a…
RT @TheTuringPost: A must-read paper → Fundamentals of Building Autonomous LLM Agents Reviews the core cognitive subsystems that make up a…
RT @TheTuringPost: A must-read paper → Fundamentals of Building Autonomous LLM Agents Reviews the core cognitive subsystems that make up a…
RT @TheTuringPost: A must-read paper → Fundamentals of Building Autonomous LLM Agents Reviews the core cognitive subsystems that make up a…
RT @TheTuringPost: A must-read paper → Fundamentals of Building Autonomous LLM Agents Reviews the core cognitive subsystems that make up a…
RT @TheTuringPost: A must-read paper → Fundamentals of Building Autonomous LLM Agents Reviews the core cognitive subsystems that make up a…
RT @TheTuringPost: A must-read paper → Fundamentals of Building Autonomous LLM Agents Reviews the core cognitive subsystems that make up a…
RT @TheTuringPost: A must-read paper → Fundamentals of Building Autonomous LLM Agents Reviews the core cognitive subsystems that make up a…
RT @TheTuringPost: A must-read paper → Fundamentals of Building Autonomous LLM Agents Reviews the core cognitive subsystems that make up a…
RT @TheTuringPost: A must-read paper → Fundamentals of Building Autonomous LLM Agents Reviews the core cognitive subsystems that make up a…
RT @TheTuringPost: A must-read paper → Fundamentals of Building Autonomous LLM Agents Reviews the core cognitive subsystems that make up a…
RT @TheTuringPost: A must-read paper → Fundamentals of Building Autonomous LLM Agents Reviews the core cognitive subsystems that make up a…
RT @TheTuringPost: A must-read paper → Fundamentals of Building Autonomous LLM Agents Reviews the core cognitive subsystems that make up a…
RT @TheTuringPost: A must-read paper → Fundamentals of Building Autonomous LLM Agents Reviews the core cognitive subsystems that make up a…
This study combined the power of Seasonal Autoregressive Integrated Moving Average (SARIMA) and Long Short-Term Memory (LSTM) neural networks to evaluate the impact of interventions on visceral leishmaniasis in Yangquan, China.
The researchers trained long short-term memory (LSTM) RNNs to recognize speech from auditory spectrograms and found that the internal dynamics of these RNNs predicted human neural population responses to the same stimuli, beyond what could be predicted from the auditory features alone.
LSTM Forecast of Stock Close Price Source: Finance & Economics Dataset (2000–2025), modeled using Python (TensorFlow/Keras). Model Overview The Long Short-Term Memory (LSTM) network was trained on daily stock closing prices extracted from the Finance & Economics Dataset.Unlike ARIMA, which assumes…
The model analyzed video sequences of 1, 10, and 50 seconds, using a convolutional neural network with a pre-trained ResNet-50 base and a long short-term memory layer.
Emmanuel Boadi: Bitcoin Price Forecasting Based on Hybrid Variational Mode Decomposition and Long Short Term Memory Network https://arxiv.org/abs/2510.15900 https://arxiv.org/pdf/2510.15900 https://arxiv.org/html/2510.15900
This study developed a weighted fusion framework that integrates transfer learning with a hybrid long short-term memory-multilayer perceptron (LSTM-MLP) model and the eXtreme Gradient Boosting (XGBoost) algorithm.
Forecasting Nigerian Equity Stock Returns Using Long Short-Term Memory Technique: Adebola K. Ojo; Ifechukwude Jude Okafor
This study developed a climate-informed early warning system for urban water pipe leakage using Long Short-Term Memory (LSTM) models.
Forecasting Nigerian Equity Stock Returns Using Long Short-Term Memory Technique: Adebola K. Ojo; Ifechukwude Jude Okafor
Back in February 2024, available online first “Application of empirical wavelet transform, particle swarm optimization, gravitational search algorithm and long short-term memory neural network to copper price forecasting” by Y.-H. Kim, S.-J. Ham & W.-S. Ri. link.springer.com/article/10.1... #EconSky
A deep learning framework predicts EDCs directly from room geometry and surface absorption; Normalized room features are provided to a long short-term memory (LSTM) network that maps configuration to EDC; generalizes across diverse rooms and supports efficient room-acoustics modeling.
The methodology combines Convolutional Neural Networks (CNN) and Long Short-Term Memory (LSTM) for load prediction, a hybrid bio-inspired optimization technique (OOA-PSO) for feature selection, and Deep Reinforcement Learning (DRL) for dynamic task scheduling.
#ML & #DL models improve #CKD to #EndStage #Renal Disease #prediction, enhancing clinical decision-making & reducing healthcare costs. Integrated data models outperform single-source models, with long short-term memory achieving high AUROC & F1 scores. www.pharmacytimes.com/view/machine...
Too long: short-term memory is too fleeting to last that long.
R. R. Dhala, A. V. S. P. Kumar and S. P. Panda, "Legal Document Information Retrieval using Long Short Term Memory-Based Domain Classification Technique," 2025 doi: 10.1109/ISAC364032.2025.11156333. ieeexplore.ieee.org/abstract/doc...
Federated Learning for Financial Forecasting Manuel Noseda, Alberto De Luca, Lukas Von Briel, Nathan Lacour http://arxiv.org/abs/2509.16393
Federated Learning for Financial Forecasting Manuel Noseda, Alberto De Luca, Lukas Von Briel, Nathan Lacour http://arxiv.org/abs/2509.16393
The GND memristor demonstrated its versatility by successfully executing stateful Boolean logic and implementing long short-term memory network cores for high-accuracy temporal sequence prediction tasks.
My inner circle
#PreprintOfTheWeek: Long Short-Term Memory Networks for Image Enhancement and Restoration ✨ Exploring LSTM models to tackle denoising, deblurring & artifact removal in images.
Using long short term memory networks to predict daily-averaged sea level anomaly and surface currents
Younggeol Cho, Gokhan Solak, Olivia Nocentini, Marta Lorenzini, Andrea Fortuna, Arash Ajoudani Anticipatory Fall Detection in Humans with Hybrid Directed Graph Neural Networks and Long Short-Term Memory https://arxiv.org/abs/2509.05337
Cho, Solak, Nocentini, Lorenzini, Fortuna, Ajoudani: Anticipatory Fall Detection in Humans with Hybrid Directed Graph Neural Networks and Long Short-Term Memory https://arxiv.org/abs/2509.05337 https://arxiv.org/pdf/2509.05337 https://arxiv.org/html/2509.05337
[2025-09-09]
iMTI-Net, an improved multi-target intelligibility prediction network, combines Whisper embeddings with statistical features and a scalar long short-term memory network, outperforming MTI-Net.
Md. Jahidul Islam Razin, Md. Abdul Karim, M. F. Mridha, S M Rafiuddin, Tahira Alam: A Long Short-Term Memory (LSTM) Model for Business Sentiment Analysis Based on Recurrent Neural Network https://arxiv.org/abs/2509.03060 https://arxiv.org/pdf/2509.03060 https://arxiv.org/html/2509.03060
Md. Jahidul Islam Razin, Md. Abdul Karim, M. F. Mridha, S M Rafiuddin, Tahira Alam A Long Short-Term Memory (LSTM) Model for Business Sentiment Analysis Based on Recurrent Neural Network https://arxiv.org/abs/2509.03060
Paper: StoxLSTM: A Stochastic Extended Long Short-Term Memory Network for Time Series Forecasting ( arxiv.org/abs/2509.01187 )
Social Media as an Emotional Barometer: Bidirectional Encoder Representations From Transformers–Long Short-Term Memory Sentiment Analysis on the Evolution of Public Sentiments During Influenza A on Sina Weibo
Solved CS310 Assignment 4: Long Short-Term Memory for Named Entity Recognition Tasks Train a bidirectional LSTM model on the CoNLL2003 English named entity recognition task set and evaluate its performance. Submit • The modified notebook files A4_ner.ipynb • A write-up document in Word/PDF…
Kong Mun Yeen, Rafidah Md Noor, Wahidah Md Shah, Aslinda Hassan, Muhammad Umair Munir Forecasting Future DDoS Attacks Using Long Short Term Memory (LSTM) Model https://arxiv.org/abs/2509.02076
Zihao Wang, Yunjie Li, Lingmin Zan, Zheng Gong, Mengtao Zhu: StoxLSTM: A Stochastic Extended Long Short-Term Memory Network for Time Series Forecasting https://arxiv.org/abs/2509.01187 https://arxiv.org/pdf/2509.01187 https://arxiv.org/html/2509.01187
Kong Mun Yeen, Rafidah Md Noor, Wahidah Md Shah, Aslinda Hassan, Muhammad Umair Munir: Forecasting Future DDoS Attacks Using Long Short Term Memory (LSTM) Model https://arxiv.org/abs/2509.02076 https://arxiv.org/pdf/2509.02076 https://arxiv.org/html/2509.02076
LSTM Enhances Dynamic Museum Visitor Interest Prediction In a groundbreaking study that could revolutionize the way museums interact with their visitors, researcher S. Nie has introduced a dynamic prediction and recommendation system that utilizes Long Short-Term Memory networks (LSTM). This deep…
Georgios Vamvouras, Konstantinos Braimakis, Christos Tzivanidis: An Explainable, Attention-Enhanced, Bidirectional Long Short-Term Memory Neural Network for Joint 48-Hour Forecasting of Tempe... https://arxiv.org/abs/2508.21109 https://arxiv.org/pdf/2508.21109 https://arxiv.org/html/2508.21109
i read a couple more papers today, tryna get a clearer understanding of memory and attention mechanisms in recurrent neural networks i think i'm going to have to give up on finding my marked up copy of the transformer paper and start over (which might actually be a good thing)
To-do-list that's too long, short-term memory loss, shopping list or a local social media influencer publicity stunt. Yes, it's a real car and yes, it was covered in Post-it notes - hundreds of them. Local influencer doing a publicity stunt.
it's well-written so it's easy to understand their model and their contribution. they're using a neural network architecture called long short-term memory, which was proposed in the 90s as a way to address the vanishing gradient problem in recurrent neural networks with long-term dependencies […]
still can't find my marked up copy of the transformer paper, so i'll read this earlier google paper instead. like yesterday, this paper abstracts machine translation as a sequence-to-sequence learning problem. long sentences are hard and the google paper has some fresh ideas.
the intro section was a whole journey! the first sentence alone Recurrent neural networks, long short-term memory and gated recurrent neural networks in particular, have been firmly established as state of the art approaches in sequence modeling and […] [Original post on a2mi.social]
Forecasting Mangrove Change with LSTM Neural Networks In a groundbreaking study that marries the realms of artificial intelligence and environmental conservation, researchers are harnessing the power of long short-term memory (LSTM) neural networks to predict changes in mangrove ecosystems in blue…
Impressed by this research:
Samuel Yen-Chi Chen, Prayag Tiwari: Quantum Long Short-term Memory with Differentiable Architecture Search https://arxiv.org/abs/2508.14955 https://arxiv.org/pdf/2508.14955 https://arxiv.org/html/2508.14955
It appears that Rubio has long & short term memory issues.
This study explores the use of Bidirectional Long Short-Term Memory (BiLSTM) networks to classify human emotions based on electroencephalography (EEG) signals. The researchers evaluated the model's performance on four well-established datasets: SEED, SEED-IV, SEED-V, and DEAP.
To be honest, it was a struggle to get this Ollama AI Model up to speed on my little mini pc. But at the moment it’s doing its best. Even when you ask it to spit out code, it’s pretty fast. Even when there is a long short term memory, it does ok. Really happy about the progress made.
Yu-Chao Hsu, Jiun-Cheng Jiang, Chun-Hua Lin, Wei-Ting Chen, Kuo-Chung Peng, Prayag Tiwari, Samuel Yen-Chi Chen, En-Jui Kuo Federated Quantum Kernel-Based Long Short-term Memory for Human Activity Recognition https://arxiv.org/abs/2508.06078
Hsu, Jiang, Lin, Chen, Peng, Tiwari, Chen, Kuo: Federated Quantum Kernel-Based Long Short-term Memory for Human Activity Recognition https://arxiv.org/abs/2508.06078 https://arxiv.org/pdf/2508.06078 https://arxiv.org/html/2508.06078
Federated Quantum Kernel-Based Long Short-term Memory for Human Activity Recognition https://arxiv.org/pdf/2508.06078 Yu-Chao Hsu, Jiun-Cheng Jiang, Chun-Hua Lin, Wei-Ting Chen, Kuo-Chung Peng, Prayag Tiwari, Samuel Yen-Chi Chen, En-Jui Kuo.
This study combines Long Short-Term Memory (LSTM) networks and Particle Swarm Optimization (PSO) to improve rainfall forecasting accuracy in the Cuddalore region.
New JMIR MedInform: Predictive Modeling of Osteonecrosis of the Femoral Head Progression Using #mobileNetV3_Large and Long Short-Term Memory Network: Novel Approach
Open Access UCL Research: Generation of Novel Fuels Optimized for High-Knock Resistance with a Long Short-Term Memory Model discovery.ucl.ac.uk/id/eprint/10...
New developments in
Reading about impressive research:
A Privacy-Preserving Federated Framework with Hybrid Quantum-Enhanced Learning for Financial Fraud Detection Abhishek Sawaika, Swetang Krishna, Tushar Tomar, Durga Pritam Suggisetti, Aditi Lal, Tanmaya Shrivastav, Nouhaila Innan, Muhammad Shafique http://arxiv.org/abs/2507.22908
A Privacy-Preserving Federated Framework with Hybrid Quantum-Enhanced Learning for Financial Fraud Detection Abhishek Sawaika, Swetang Krishna, Tushar Tomar, Durga Pritam Suggisetti, Aditi Lal, Tanmaya Shrivastav, Nouhaila Innan, Muhammad Shafique http://arxiv.org/abs/2507.22908
Energy storage progress: ⚡ Study highlights how improved state of health estimation for lithium-ion batteries via multidimensional health features and long short-term memory modeling cou... www.sciencedirect.com/science/arti... #Sustainability #battchat
CW3E Publication Notice: "Global Daily Discharge Estimation Based on Grid Long Short-Term Memory (LSTM) Model and River Routing" in @agu.org's Water Resources Research. For a summary of this paper, visit: cw3e.ucsd.edu/cw3e-publica....
[2025-07-18]
No wonder it is the symbol of the Republican party. Can never remember those promises. Although I also think at this point Donkey's may also have long & short term memory problems as well.
Makoto Takagi, Ryuji Kokubo, Misato Kurosawa, Tsubasa Ikami, Yasuhiro Egami, ... Time-series forecasting for nonlinear high-dimensional system using hybrid method combining autoencoder and multi-parallelized quantum long short-term memory and gated recurrent unit https://arxiv.org/abs/2507.10876
Makoto Takagi, et al.: Time-series forecasting for nonlinear high-dimensional system using hybrid method combining autoencoder and multi-parallelized quantum long short-term memory and gated ... https://arxiv.org/abs/2507.10876 https://arxiv.org/pdf/2507.10876 https://arxiv.org/html/2507.10876
Time-series forecasting for nonlinear high-dimensional system using hybrid method combining autoencoder and multi-parallelized quantum long short-term memory and gated recurrent unit https://arxiv.org/pdf/2507.10876 Makoto Takagi et al.
Understanding LSTM (Long Short Term Memory) Networks http://colah.github.io/posts/2015-08-Understanding-LSTMs/ (Oldie but goodie)
Yuyang Lou, Charles Li Dynamic Long Short-Term Memory Based Memory Storage For Long Horizon LLM Interaction https://arxiv.org/abs/2507.03042
Yuyang Lou, Charles Li: Dynamic Long Short-Term Memory Based Memory Storage For Long Horizon LLM Interaction https://arxiv.org/abs/2507.03042 https://arxiv.org/pdf/2507.03042 https://arxiv.org/html/2507.03042
[2025-07-08]
[2025-07-04]
@frankiethull.bsky.social do you know something about the methods used by the winners of the Biology and the Statistics price, Fast Dynamic Time Warping (FastDTW) and Long Short-Term Memory (LSTM) neural network? #RStats #PyData
Adebola K. Ojo, Ifechukwude Jude Okafor: Forecasting Nigerian Equity Stock Returns Using Long Short-Term Memory Technique https://arxiv.org/abs/2507.01964 https://arxiv.org/pdf/2507.01964 https://arxiv.org/html/2507.01964
This study offers a system that assigns energy sharing coefficients between members of an energy community based on daily consumption estimates obtained from neural networks such as LSTM (Long Short-Term Memory), in a dynamic and optimised way.
link
At the end of the day we're just meat computers. I think if an advanced LLM could run for 60~80 years and had some internal systems for long/short term memory attached to some kind of success criteria for it's existence/betterment we would probably get something resembling consciousness.
Peter Lengyel: CCLSTM: Coupled Convolutional Long-Short Term Memory Network for Occupancy Flow Forecasting https://arxiv.org/abs/2506.06128 https://arxiv.org/pdf/2506.06128 https://arxiv.org/html/2506.06128
classification with Long Short-Term Memory networks for continuous kinematic prediction, unifying discrete decision-making processes and continuous vehicular dynamics to comprehensively represent inter- and intra-driver heterogeneity. Driving regimes [5/7 of https://arxiv.org/abs/2506.05902v1]
especially during variant surges, when they were needed most. This study introduces a novel Long Short-Term Memory (LSTM) framework for forecasting daily state-level incident hospitalizations in the United States. We present a spatiotemporal feature, [2/7 of https://arxiv.org/abs/2506.05752v1]
Peter Lengyel CCLSTM: Coupled Convolutional Long-Short Term Memory Network for Occupancy Flow Forecasting https://arxiv.org/abs/2506.06128
model to capture fluctuating high-impact failure events. We evaluate two architectures: an XGBoost regressor achieving a median absolute error (MedAE) of 14.3 per cent and a Long Short-Term Memory network with a MedAE of 15.1 per cent. Shapley [3/6 of https://arxiv.org/abs/2506.04296v1]
Este estudio propone un sistema que asigne coeficientes de reparto de energía entre miembros de una comunidad energética en base a previsiones de consumo diario obtenidas de redes neuronales tipo LSTM (Long Short-Term Memory), de manera dinámica y optimizada.
link
arXiv:2506.02796v1 Announce Type: new Abstract: This paper introduces a novel multivariate volatility modeling framework, named Long Short-Term Memory enhanced BEKK (LSTM-BEKK), that integrates deep learning into multivariate GARCH processes. By [1/5 of https://arxiv.org/abs/2506.02796v1]
Long Short-Term Memory (LSTM) to gather comprehensive node and pipeline status information. Then, we implement a Reinforcement Learning (RL) algorithm based on policy gradients for online configuration decisions. 3) Experiments conducted in a real [4/5 of https://arxiv.org/abs/2506.02814v1]
SineKAN model outperforms several previously explored neural quantum state ans\"atze, including Restricted Boltzmann Machines (RBMs), Long Short-Term Memory models (LSTMs), and Feed-Forward Neural Networks (FFCN), when compared to the results obtained [4/5 of https://arxiv.org/abs/2506.01891v1]
validated their effectiveness using data from 14 military industry stocks in the Chinese A-share market. Furthermore, we integrated multi-head attention (MHA) mechanisms with the Long Short-Term Memory (LSTM) module to investigate its role in modeling [5/7 of https://arxiv.org/abs/2505.22678v1]
arXiv:2505.23084v1 Announce Type: new Abstract: This paper proposes a hybrid framework combining LSTM (Long Short-Term Memory) networks with LightGBM and CatBoost for stock price prediction. The framework processes time-series financial data and [1/5 of https://arxiv.org/abs/2505.23084v1]
Sealos-based performance optimization approach for securities trading, incorporating an adaptive resource scheduling algorithm leveraging deep reinforcement learning, a three-level caching mechanism for trading operations, and a Long Short-Term Memory [3/5 of https://arxiv.org/abs/2505.23258v1]
New developments in
identifies fraudulent behaviors in residential PV generation, thus ensuring the supply-demand balance in smart cities. Our hybrid deep learning model, combining multi-scale Convolutional Neural Network (CNN), Long Short-Term Memory (LSTM), and [3/6 of https://arxiv.org/abs/2505.18755v1]
coordinate system. In high-bitrate coding mode, we use a lightweight Long-Short-Term Memory-based predictive (LSTM-P) module that captures long-term geometry correlations between different coordinates to efficiently predict and compress the elevation [5/8 of https://arxiv.org/abs/2505.20059v1]
tree methods such as Extreme Gradient Boosting (XGBoost) and Light Gradient Boosting Machine (LightGBM). A hybrid framework is also developed. In addition, two recurrent neural network architectures, Long Short Term Memory (LSTM) networks and Gated [4/6 of https://arxiv.org/abs/2505.18170v1]
charging station with solar photovoltaics in a more realistic scenario, where system faults may occur. A Long Short-Term Memory (LSTM) network is incorporated in the MARL algorithm to extract temporal features from time-series. Additionally, a dense [4/6 of https://arxiv.org/abs/2505.18750v1]
estimating refractive power using two eye movement recording techniques: electrooculography (EOG) and video-based eye tracking. Using a publicly available dataset recorded under varying diopter conditions, we trained Long Short-Term Memory (LSTM) [2/7 of https://arxiv.org/abs/2505.18538v1]
such as Support Vector Machines (SVM), XGBoost, and Artificial Neural Networks (ANN), Long Short-Term Memory (LSTM) networks, and Gated Recurrent Units (GRU) to predict daily and multi-step river flow. The LSTM network outperformed other models, [4/7 of https://arxiv.org/abs/2505.18645v1]
incorporate information about previous environmental states into the Long Short-Term Memory (LSTM) architecture and combine it with Graph Convolutions to account for correlations between different chambers. With the usage of a proposed prediction [3/5 of https://arxiv.org/abs/2505.17781v1]
correlations of the features and forms a comprehensive feature space with existing MTSC models for classification. Here, we instantiate the proposed module to work in parallel with a Long Short-Term Memory (LSTM) network and a Causal Fully [5/7 of https://arxiv.org/abs/2505.17307v1]
arXiv:2505.17696v1 Announce Type: new Abstract: This research proposes methods for formulating and guaranteeing the resilience of long short-term memory (LSTM) networks, which can serve as a key technology in AI system quality assurance. We introduce [1/3 of https://arxiv.org/abs/2505.17696v1]
Attentional Long Short-Term Memory (A-LSTM), and Ordinary Differential Equation-based LSTM (ODE-LSTM) modules. This architecture is designed to capture both local signal characteristics and long-range temporal dependencies while modeling the [5/8 of https://arxiv.org/abs/2505.16664v1]
of artificial intelligence techniques, multiple Quantum Neural Network (QNN) models have been proposed, including quantum convolutional neural networks, quantum long short-term memory networks, and quantum generative adversarial networks. Furthermore, [2/6 of https://arxiv.org/abs/2505.15823v1]
Chang Liu Convolutional Long Short-Term Memory Neural Networks Based Numerical Simulation of Flow Field https://arxiv.org/abs/2505.15533
are twofold: first, the systematic generation and curation of a novel scheduling dataset from a running Linux kernel, capturing real-world CFS behavior; and second, the development, training, and evaluation of a Long Short-Term Memory (LSTM) network [3/5 of https://arxiv.org/abs/2505.15213v1]
consumption. Deep learning-based analysis of flow filed provides an alternative. For the task of flow field prediction, an improved Convolutional Long Short-Term Memory (Con-vLSTM) Neural Network is proposed as the baseline network in consideration of [2/5 of https://arxiv.org/abs/2505.15533v1]
Chang Liu: Convolutional Long Short-Term Memory Neural Networks Based Numerical Simulation of Flow Field https://arxiv.org/abs/2505.15533 https://arxiv.org/pdf/2505.15533 https://arxiv.org/html/2505.15533
RT @MarcoRoberti: First experiments with my Christmas gift :) A great classic by S. Hochreiter and @SchmidhuberAI https://t.co/oVL1aoXvHd…
First experiments with my Christmas gift :) A great classic by S. Hochreiter and @SchmidhuberAI https://t.co/oVL1aoXvHd #LSTM #DeepLearning #NLP https://t.co/4utG3f769n
PS
SB
IT
RT
FM
JE
AC
お
HM
R
CG
KC
小D
BO
SL
GR
DG
FE
ES
L
AD
H
RC
DS
E
A
IG
P
IC
C
K
TS
LH
A
A
LU
CR
N
A
NP
西
DP
SE
K
NI
周S
DA
J
J
BA
D
DS
AK
BG
S
R
M
S
PX
M
KG
AD
D
克
F
L
타
SS
B
CA
H
AM
JN
E
KN
PI
AG
HJ
EM
DI
MW
A
GM
GF
SC
I
RR
O
AE
M
CE
A
PS
八
SP
PE
MR