Cortico-cerebellar networks as decoupling neural interfaces
Authors: Joseph Pemberton, Ellen Boven, Richard Apps, Rui Ponte Costa
NeurIPS 2021 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | We test this cortico-cerebellar recurrent neural network (cc RNN) 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 cc RNNs facilitates learning while reducing ataxia-like behaviours, consistent with classical experimental observations. |
| Researcher Affiliation | Academia | Joseph Pemberton Bristol Computational Neuroscience Unit Dept. of Computer Science, SCEEM University of Bristol, UK oq19042@bristol.ac.uk |
| Pseudocode | No | The paper includes model schematics but does not provide structured pseudocode or algorithm blocks. |
| Open Source Code | No | The paper does not contain any explicit statement about releasing the source code for their methodology, nor does it provide a link to a code repository. |
| Open Datasets | Yes | For the sensorimotor tasks we also test the models with different external feedback intervals. This defines how often the model has access to an external teaching signal (e.g. only every 2 timesteps). Moreover, we introduce two sensorimotor tasks which build on the classical MNIST dataset [56]. We use a standard dataset (ILSVRC-2012-CLS; Russakovsky et al. [62]) and the networks are trained to maximise the likelihood of each word given an image (SM for more details). |
| Dataset Splits | No | The paper mentions using standard datasets like MNIST and ImageNet, which typically have predefined splits. However, it does not explicitly state the training, validation, or test split percentages, sample counts, or formally cite how the data was partitioned for their specific experiments. |
| Hardware Specification | No | The paper states, 'This work made use of the HPC system Blue Pebble at the University of Bristol, UK.', but it does not provide specific hardware details such as GPU/CPU models, processor speeds, or memory amounts. |
| Software Dependencies | No | The paper does not explicitly list specific software dependencies with their version numbers, such as programming languages, libraries, or frameworks used for implementation. |
| Experiment Setup | Yes | We test this cortico-cerebellar recurrent neural network (cc RNN) model on a number of sensorimotor (line and digit drawing) and cognitive tasks (pattern recognition and caption generation)... For the sensorimotor tasks we also test the models with different external feedback intervals. This defines how often the model has access to an external teaching signal (e.g. only every 2 timesteps)... All experiments used 10 seeds. |