One-shot learning of paired association navigation with biologically plausible schemas
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2021
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866910596445765632 |
|---|---|
| author | Kumar, M Ganesh Tan, Cheston Libedinsky, Camilo Yen, Shih-Cheng Tan, Andrew Yong-Yi |
| author_facet | Kumar, M Ganesh Tan, Cheston Libedinsky, Camilo Yen, Shih-Cheng Tan, Andrew Yong-Yi |
| contents | Schemas are knowledge structures that can enable rapid learning. Rodent one-shot learning in a multiple paired association navigation task has been postulated to be schema-dependent. We still only poorly understand how schemas, conceptualized at Marr's computational level, are neurally implemented. Moreover, a biologically plausible computational model of the rodent learning has not been demonstrated. Accordingly, we here compose an agent from schemas with biologically plausible neural implementations. The agent gradually learns a metric representation of its environment using a path integration temporal difference error, allowing it to localize in any environment. Additionally, the agent contains an associative memory that can stably form numerous one-shot associations between sensory cues and goal coordinates, implemented with a feedforward layer or a reservoir of recurrently connected neurons whose plastic output weights are governed by a 4-factor reward-modulated Exploratory Hebbian (EH) rule. A third network performs vector subtraction between the agent's current and goal location to decide the direction of movement. We further show that schemas supplemented by an actor-critic allows the agent to succeed even if an obstacle prevents direct heading, and that temporal-difference learning of a working memory gating mechanism enables one-shot learning despite distractors. Our agent recapitulates learning behavior observed in experiments and provides testable predictions that can be probed in future experiments. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2106_03580 |
| institution | arXiv |
| publishDate | 2021 |
| record_format | arxiv |
| spellingShingle | One-shot learning of paired association navigation with biologically plausible schemas Kumar, M Ganesh Tan, Cheston Libedinsky, Camilo Yen, Shih-Cheng Tan, Andrew Yong-Yi Neural and Evolutionary Computing Neurons and Cognition Schemas are knowledge structures that can enable rapid learning. Rodent one-shot learning in a multiple paired association navigation task has been postulated to be schema-dependent. We still only poorly understand how schemas, conceptualized at Marr's computational level, are neurally implemented. Moreover, a biologically plausible computational model of the rodent learning has not been demonstrated. Accordingly, we here compose an agent from schemas with biologically plausible neural implementations. The agent gradually learns a metric representation of its environment using a path integration temporal difference error, allowing it to localize in any environment. Additionally, the agent contains an associative memory that can stably form numerous one-shot associations between sensory cues and goal coordinates, implemented with a feedforward layer or a reservoir of recurrently connected neurons whose plastic output weights are governed by a 4-factor reward-modulated Exploratory Hebbian (EH) rule. A third network performs vector subtraction between the agent's current and goal location to decide the direction of movement. We further show that schemas supplemented by an actor-critic allows the agent to succeed even if an obstacle prevents direct heading, and that temporal-difference learning of a working memory gating mechanism enables one-shot learning despite distractors. Our agent recapitulates learning behavior observed in experiments and provides testable predictions that can be probed in future experiments. |
| title | One-shot learning of paired association navigation with biologically plausible schemas |
| topic | Neural and Evolutionary Computing Neurons and Cognition |
| url | https://arxiv.org/abs/2106.03580 |