On the Design Space Between Transformers and Recursive Neural Nets
Fuente:
arXiv
Guardado en:
| Autores principales: | , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866913490508185600 |
|---|---|
| author | Chowdhury, Jishnu Ray Caragea, Cornelia |
| author_facet | Chowdhury, Jishnu Ray Caragea, Cornelia |
| contents | In this paper, we study two classes of models, Recursive Neural Networks (RvNNs) and Transformers, and show that a tight connection between them emerges from the recent development of two recent models - Continuous Recursive Neural Networks (CRvNN) and Neural Data Routers (NDR). On one hand, CRvNN pushes the boundaries of traditional RvNN, relaxing its discrete structure-wise composition and ends up with a Transformer-like structure. On the other hand, NDR constrains the original Transformer to induce better structural inductive bias, ending up with a model that is close to CRvNN. Both models, CRvNN and NDR, show strong performance in algorithmic tasks and generalization in which simpler forms of RvNNs and Transformers fail. We explore these "bridge" models in the design space between RvNNs and Transformers, formalize their tight connections, discuss their limitations, and propose ideas for future research. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2409_01531 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | On the Design Space Between Transformers and Recursive Neural Nets Chowdhury, Jishnu Ray Caragea, Cornelia Machine Learning Artificial Intelligence In this paper, we study two classes of models, Recursive Neural Networks (RvNNs) and Transformers, and show that a tight connection between them emerges from the recent development of two recent models - Continuous Recursive Neural Networks (CRvNN) and Neural Data Routers (NDR). On one hand, CRvNN pushes the boundaries of traditional RvNN, relaxing its discrete structure-wise composition and ends up with a Transformer-like structure. On the other hand, NDR constrains the original Transformer to induce better structural inductive bias, ending up with a model that is close to CRvNN. Both models, CRvNN and NDR, show strong performance in algorithmic tasks and generalization in which simpler forms of RvNNs and Transformers fail. We explore these "bridge" models in the design space between RvNNs and Transformers, formalize their tight connections, discuss their limitations, and propose ideas for future research. |
| title | On the Design Space Between Transformers and Recursive Neural Nets |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2409.01531 |