Krahasoni metodat
Shqyrtoni metodat e zgjedhura krah për krah; rreshtat që ndryshojnë janë të theksuar.
| LSTM e Shpjegueshme× | Long Short-Term Memory (LSTM)× | |
|---|---|---|
| Fusha | Mësimi i thellë | Mësimi i thellë |
| Familja | Machine learning | Machine learning |
| Viti i origjinës≠ | 2017–2019 | 1997 |
| Krijuesi≠ | Lundberg & Lee (SHAP); Ribeiro et al. (LIME); community synthesis | Hochreiter, S. & Schmidhuber, J. |
| Lloji≠ | Interpretable deep learning (post-hoc explainability) | Recurrent neural network with gated memory cells |
| Burimi themelues≠ | Lundberg, S. M., & Lee, S.-I. (2017). A unified approach to interpreting model predictions. Advances in Neural Information Processing Systems, 30, 4765–4774. link ↗ | Hochreiter, S. & Schmidhuber, J. (1997). Long short-term memory. Neural Computation, 9(8), 1735–1780. DOI ↗ |
| Emërtime të tjera | XAI-LSTM, interpretable LSTM, LSTM with SHAP, transparent LSTM | LSTM, LSTM network, LSTM-RNN, long short-term memory RNN |
| Të lidhura≠ | 5 | 4 |
| Përmbledhja≠ | Explainable LSTM pairs a trained Long Short-Term Memory network with post-hoc interpretability techniques — chiefly SHAP, LIME, integrated gradients, or attention visualization — to reveal which time steps, tokens, or features drive each prediction. It bridges the accuracy of recurrent deep learning with the transparency demanded by high-stakes domains such as clinical decision support, fraud detection, and regulatory compliance. | Long Short-Term Memory (LSTM) is a gated recurrent neural network architecture introduced by Hochreiter and Schmidhuber in 1997. It was designed to learn dependencies across long sequences by using dedicated memory cells and three learned gates — forget, input, and output — that control what information is retained, updated, or passed forward at each time step. |
| ScholarGateSeti i të dhënave ↗ |
|
|