Compară metode
Examinează metodele selectate una lângă alta; rândurile care diferă sunt evidențiate.
| LSTM× | Modelul Rasch× | |
|---|---|---|
| Domeniu≠ | Învățare profundă | Psihometrie |
| Familie≠ | Machine learning | Latent structure |
| Anul apariției≠ | 1997 | 1960 |
| Autorul original≠ | Hochreiter, S. & Schmidhuber, J. | Georg Rasch |
| Tip≠ | Recurrent neural network (gated memory cell) | Item Response Theory / Latent trait model |
| Sursa seminală≠ | Hochreiter, S. & Schmidhuber, J. (1997). Long Short-Term Memory. Neural Computation, 9(8), 1735–1780. DOI ↗ | Rasch, G. (1960). Probabilistic Models for Some Intelligence and Attainment Tests. Danish Institute for Educational Research, Copenhagen. link ↗ |
| Denumiri alternative | LSTM (Uzun Kısa Dönem Bellek Ağı), long short-term memory, LSTM network, recurrent neural network with memory cells | 1PL IRT, one-parameter logistic model, Rasch Modeli — 1PL IRT, 1PL model |
| Înrudite≠ | 5 | 6 |
| Rezumat≠ | LSTM (Long Short-Term Memory) is a recurrent neural network architecture, introduced by Sepp Hochreiter and Jürgen Schmidhuber in 1997, that can learn long-term dependencies in sequential data and is widely used for time-series and sequence prediction. It keeps an internal memory that lets information persist across many time steps. | The Rasch model, introduced by Georg Rasch in 1960, is the simplest member of the Item Response Theory (IRT) family. It assigns a single difficulty parameter to each test item and places both item difficulties and person abilities on the same logit scale, enabling direct, sample-independent comparison of items and persons. |
| ScholarGateSet de date ↗ |
|
|