Abstract representations emerge naturally in neural networks trained to perform multiple tasks

These are the simulation data that underly some of the figures in this paper: https://doi.org/10.1101/2021.10.20.465187 <br> In particular, these data save the arguments, generalization metrics, and some other details from the simulations showing how generalization depends on the number of tasks. In most cases, they do not save the underlying model or samples from the underlying model -- though the code for training such models is provided in the github repository linked below. <br> More information about these data and code for reading them and replotting the figures in the paper can be found here: https://github.com/wj2/disentangled

本数据集为支撑论文https://doi.org/10.1101/2021.10.20.465187 中部分图表的仿真实验数据。
具体而言，本数据集存储了本次仿真实验的运行参数、泛化指标，以及反映泛化性能随任务数量变化规律的其余仿真细节。多数情况下，本数据集未存储底层模型或底层模型的采样数据——不过相关模型的训练代码已在下文链接的GitHub仓库中提供。
有关本数据集的更多信息、数据集读取代码以及复刻本文图表的代码，可通过以下链接获取：https://github.com/wj2/disentangled