Burst-dependent plasticity and dendritic amplification support target-based learning and hierarchical imitation learning
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2022
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866914461879631872 |
|---|---|
| author | Capone, Cristiano Lupo, Cosimo Muratore, Paolo Paolucci, Pier Stanislao |
| author_facet | Capone, Cristiano Lupo, Cosimo Muratore, Paolo Paolucci, Pier Stanislao |
| contents | The brain can learn to solve a wide range of tasks with high temporal and energetic efficiency. However, most biological models are composed of simple single compartment neurons and cannot achieve the state-of-art performances of artificial intelligence. We propose a multi-compartment model of pyramidal neuron, in which bursts and dendritic input segregation give the possibility to plausibly support a biological target-based learning. In target-based learning, the internal solution of a problem (a spatio temporal pattern of bursts in our case) is suggested to the network, bypassing the problems of error backpropagation and credit assignment. Finally, we show that this neuronal architecture naturally support the orchestration of hierarchical imitation learning, enabling the decomposition of challenging long-horizon decision-making tasks into simpler subtasks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2201_11717 |
| institution | arXiv |
| publishDate | 2022 |
| record_format | arxiv |
| spellingShingle | Burst-dependent plasticity and dendritic amplification support target-based learning and hierarchical imitation learning Capone, Cristiano Lupo, Cosimo Muratore, Paolo Paolucci, Pier Stanislao Neurons and Cognition The brain can learn to solve a wide range of tasks with high temporal and energetic efficiency. However, most biological models are composed of simple single compartment neurons and cannot achieve the state-of-art performances of artificial intelligence. We propose a multi-compartment model of pyramidal neuron, in which bursts and dendritic input segregation give the possibility to plausibly support a biological target-based learning. In target-based learning, the internal solution of a problem (a spatio temporal pattern of bursts in our case) is suggested to the network, bypassing the problems of error backpropagation and credit assignment. Finally, we show that this neuronal architecture naturally support the orchestration of hierarchical imitation learning, enabling the decomposition of challenging long-horizon decision-making tasks into simpler subtasks. |
| title | Burst-dependent plasticity and dendritic amplification support target-based learning and hierarchical imitation learning |
| topic | Neurons and Cognition |
| url | https://arxiv.org/abs/2201.11717 |