Long Short Term Memory
Long Short-Term Memory (LSTM) networks are a type of recurrent neural network designed to process sequential data by learning long-term dependencies, enabling accurate predictions and classifications in various applications. Current research focuses on enhancing LSTM architectures, such as incorporating convolutional layers, attention mechanisms, and hybrid models combining LSTMs with other deep learning techniques like transformers or graph neural networks, to improve efficiency and accuracy. This work is significant because LSTMs are proving highly effective across diverse fields, from financial forecasting and environmental monitoring to medical image analysis and activity recognition, offering powerful tools for analyzing complex temporal data.
Papers
A Computer Vision Based Approach for Stalking Detection Using a CNN-LSTM-MLP Hybrid Fusion Model
Murad Hasan, Shahriar Iqbal, Md. Billal Hossain Faisal, Md. Musnad Hossin Neloy, Md. Tonmoy Kabir, Md. Tanzim Reza, Md. Golam Rabiul Alam, Md Zia Uddin
An Attention Long Short-Term Memory based system for automatic classification of speech intelligibility
Miguel Fernández-Díaz, Ascensión Gallardo-Antolín