Joseph Pemberton, Ellen Boven, Richard Apps, Rui Ponte Costa
We lifted 12 functions out of this paper's own repositories and ran 9 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.
| Repository | Role | Ran |
|---|---|---|
| neuralml/ccdni | canonical | 7 of 8 |
| koz4k/dni-pytorch | unrelated | 2 of 4 |
| Function | Status | Where it lives |
|---|---|---|
| BackwardInterface | Ran | neuralml/ccdni/src/dni.py pointer only (licence: NONE) · get_code("a93206440f7a897c") |
| ForwardInterface | Ran | neuralml/ccdni/src/dni.py pointer only (licence: NONE) · get_code("bc34e4b901e776ff") |
| ForwardInterface | Ran | koz4k/dni-pytorch/dni.py code served (permissive licence) · get_code("8ef0406bf25d2ddf") |
| UnidirectionalInterface | Ran | neuralml/ccdni/src/dni.py pointer only (licence: NONE) · get_code("758c7c237fe33875") |
| UnidirectionalInterface | Ran | koz4k/dni-pytorch/dni.py code served (permissive licence) · get_code("3732c152de7ddb6e") |
| _Manager | Ran | neuralml/ccdni/src/dni.py pointer only (licence: NONE) · get_code("642b4288d66b9bce") |
| _SyntheticGradientUpdater | Ran | neuralml/ccdni/src/dni.py pointer only (licence: NONE) · get_code("fed9864cbd49eff5") |
| _ones_like | Ran | neuralml/ccdni/src/dni.py pointer only (licence: NONE) · get_code("c3036c0ca8077c51") |
| defer_backward | Ran | neuralml/ccdni/src/dni.py pointer only (licence: NONE) · get_code("373d3936bcca86fb") |
| BackwardInterface | Not yet run | koz4k/dni-pytorch/dni.py code served (permissive licence) · get_code("1ecf7b307455a0db") |
| BidirectionalInterface | Not yet run | neuralml/ccdni/src/dni.py pointer only (licence: NONE) · get_code("62959a2085c5a16f") |
| BidirectionalInterface | Not yet run | koz4k/dni-pytorch/dni.py code served (permissive licence) · get_code("a929055939c35741") |
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
The brain solves the credit assignment problem remarkably well. For credit to be assigned across neural networks they must, in principle, wait for specific neural computations to finish. How the brain deals with this inherent locking problem has remained unclear. Deep learning methods suffer from similar locking constraints both on the forward and feedback phase. Recently, decoupled neural interfaces (DNIs) were introduced as a solution to the forward and feedback locking problems in deep networks. Here we propose that a specialised brain region, the cerebellum, helps the cerebral cortex solve similar locking problems akin to DNIs. To demonstrate the potential of this framework we introduce a systems-level model in which a recurrent cortical network receives online temporal feedback predictions from a cerebellar module. We test this cortico-cerebellar recurrent neural network (ccRNN) model on a number of sensorimotor (line and digit drawing) and cognitive tasks (pattern recognition and caption generation) that have been shown to be cerebellar-dependent. In all tasks, we observe that ccRNNs facilitates learning while reducing ataxia-like behaviours, consistent with classical experimental observations. Moreover, our model also explains recent behavioural and neuronal observations while making several testable predictions across multiple levels. Overall, our work offers a novel perspective on the cerebellum as a brainwide decoupling machine for efficient credit assignment and opens a new avenue between deep learning and neuroscience.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2110.11501")
get_code_for_paper("2110.11501")
have("2110.11501")
Connect an agent — have() is free.