# Cortico-cerebellar networks as decoupling neural interfaces

arXiv: https://arxiv.org/abs/2110.11501 · HTML: https://mlsanity.com/paper/2110.11501/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 80 references that are in the map.
- First posted on arXiv 21 Oct 2021.

## Builds on (most cited first, 18 of 18)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification](https://mlsanity.com/paper/1502.01852/) (2015)
- [CIDEr: Consensus-based Image Description Evaluation](https://mlsanity.com/paper/1411.5726/) (2014)
- [SPICE: Semantic Propositional Image Caption Evaluation](https://mlsanity.com/paper/1607.08822/) (2016)
- [Difference Target Propagation](https://mlsanity.com/paper/1412.7525/) (2014)
- [Decoupled Neural Interfaces using Synthetic Gradients](https://mlsanity.com/paper/1608.05343/) (2016)
- [A Simple Way to Initialize Recurrent Networks of Rectified Linear Units](https://mlsanity.com/paper/1504.00941/) (2015)
- [Dendritic cortical microcircuits approximate the backpropagation algorithm](https://mlsanity.com/paper/1810.11393/) (2018)
- [Towards an integration of deep learning and neuroscience](https://mlsanity.com/paper/1606.03813/) (2016)
- [Decoupled Greedy Learning of CNNs](https://mlsanity.com/paper/1901.08164/) (2019)
- [Towards deep learning with segregated dendrites](https://mlsanity.com/paper/1610.00161/) (2016)
- [Biologically inspired alternatives to backpropagation through time for learning in recurrent neural nets](https://mlsanity.com/paper/1901.09049/) (2019)
- [GAIT-prop: A biologically plausible learning rule derived from backpropagation of error](https://mlsanity.com/paper/2006.06438/) (2020)
- [Fully Decoupled Neural Network Learning Using Delayed Gradients](https://mlsanity.com/paper/1906.09108/) (2019)
- [Cortical microcircuits as gated-recurrent neural networks](https://mlsanity.com/paper/1711.02448/) (2017)
- [Local Critic Training of Deep Neural Networks](https://mlsanity.com/paper/1805.01128/) (2018)

## Built on by (most cited first, 4 of 4)

- [Single-phase deep learning in cortico-cortical networks](https://mlsanity.com/paper/2206.11769/) (2022)
- [BP(λ): Online Learning via Synthetic Gradients](https://mlsanity.com/paper/2401.07044/) (2024)
- [Is Backpropagation Optimal? When Synthetic Gradients Improve Sample Efficiency](https://mlsanity.com/paper/2605.27946/) (2026)
- [Error- and Prediction-Driven Motor Learning in the Cortico-Cerebellar Loop](https://mlsanity.com/paper/2609.29945/) (2026)

## Abstract (arXiv)

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 brain-wide decoupling machine for efficient credit assignment and opens a new avenue between deep learning and neuroscience.