Are you an EPFL student looking for a semester project?
Work with us on data science and visualisation projects, and deploy your project as an app on top of Graph Search.
Here we provide the neural data, activation and predictions for the best models and result dataframes of our article "Task-driven neural network models predict neural dynamics of proprioception". It contains the behavioral and neural experimental data (cuneate nucleus and somatosensory recordings from the Miller Lab, Northwestern University), the result dataframes for task-driven and untrained models, the activations and predictions for the best models for all tasks for active and passive movements and the predictions for linear models for active and passive movements. Note, the predictions of other models can be computed from the network weights that were deposited for all trained models. The overall structure of the data is: └── exp_analysis ├── results - Contains the result dataframe of the predictions for all models, tasks and primates ├── activations │ ├── active - Contains activations related to active movements │ └── passive - Contains activations related to passive movements ├── predictions │ ├── active - Contains predictions related to active movements │ └── passive - Contains predictions related to passive movements └── beh_exp_datasets ├── matlab_data - Contains raw behavioral and neural data ├── MonkeyAlignedDatasets_new - Contains padded test behavioral input for generating network activations ├── MonkeyDatasets - Contains not aligned padded test behavioral input for generating network activations ├── MonkeySpikeRegressDatasets - Contains datasets for training data-driven models ├── MonkeySpikeRegressDatasets_new - Contains trial index for regression splits └── new_beh_exp_dataframe - Contains pre-processed behavioral and neural data
Pascal Fua, Mathieu Salzmann, Krzysztof Maciej Lis, Sina Honari
Olaf Blanke, Lukas Heydrich, Eva Blondiaux
Alexander Mathis, Alberto Silvio Chiappa, Alessandro Marin Vargas, Axel Bisi