This article provides a beginner-friendly explanation of attention mechanisms and transformer models, covering sequence-to-sequence modeling, the limitations of RNNs, the concept of attention, and how transformers address these limitations with self-attention and parallelization.
A new LSTM model, sLSTM, is introduced to improve long-term time series forecasting accuracy. It's evaluated on benchmark datasets and compared to other state-of-the-art methods.
An illustrated and intuitive guide on the inner workings of an LSTM, which are an improvement on Recurrent Neural Networks (RNNs) that struggle with retaining information over long distances.
