Сравнение на методи
Прегледайте избраните методи един до друг; редовете с разлики са откроени.
| LSTM× | Случайна гора× | Трансформър (обработка на естествен език)× | |
|---|---|---|---|
| Област≠ | Дълбоко обучение | Машинно обучение | Дълбоко обучение |
| Семейство | Machine learning | Machine learning | Machine learning |
| Година на възникване≠ | 1997 | 2001 | 2017 |
| Създател≠ | Hochreiter, S. & Schmidhuber, J. | Breiman, L. | Vaswani, A. et al. |
| Тип≠ | Recurrent neural network (gated memory cell) | Ensemble (bagging of decision trees) | Attention-based deep neural network |
| Основополагащ източник≠ | Hochreiter, S. & Schmidhuber, J. (1997). Long Short-Term Memory. Neural Computation, 9(8), 1735–1780. DOI ↗ | Breiman, L. (2001). Random Forests. Machine Learning, 45, 5–32. DOI ↗ | Vaswani, A. et al. (2017). Attention Is All You Need. NeurIPS. link ↗ |
| Други названия | LSTM (Uzun Kısa Dönem Bellek Ağı), long short-term memory, LSTM network, recurrent neural network with memory cells | Rastgele Orman (Random Forest), rastgele orman, random decision forest, bagged tree ensemble | Transformer Modeli (NLP), attention-based language model, self-attention network, transformer NLP |
| Свързани≠ | 5 | 4 | 4 |
| Резюме≠ | 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. | Random Forest is an ensemble learning method, introduced by Leo Breiman in 2001, that grows many decision trees on bootstrap samples of the data and combines their votes to produce strong classification and regression. By pooling many slightly different trees, it produces more accurate and more stable predictions than any single tree. | The Transformer is an attention-based deep learning model, introduced by Vaswani and colleagues in 2017, that performs text classification, named-entity recognition, and language modelling by letting every token in a sequence attend directly to every other token. It replaced earlier recurrent designs with a self-attention mechanism that processes whole sequences in parallel. |
| ScholarGateНабор от данни ↗ |
|
|
|