In this study, we investigate the generalization of LSTM, ReLU and GRU models on counting tasks over long sequences. Previous theoretical work has established that RNNs with ReLU activation and LSTMs have the capacity for counting with suitable configuration, while GRUs have limitations that prevent correct counting over longer sequences. Despite this and some positive empirical results for LSTMs on Dyck-1 languages, our experimental results show that LSTMs fail to learn correct counting behavior for sequences that are significantly longer than in the training data. ReLUs show much larger variance in behavior and in most cases worse generalization. The long sequence generalization is empirically related to validation loss, but reliable long sequence generalization seems not practically achievable through backpropagation with current techniques. We demonstrate different failure modes for LSTMs, GRUs and ReLUs. In particular, we observe that the saturation of activation functions in LSTMs and the correct weight setting for ReLUs to generalize counting behavior are not achieved in standard training regimens. In summary, learning generalizable counting behavior is still an open problem and we discuss potential approaches for further research.

在爵士乐中，一种逆向是一种新的旋律，该旋律是在现有但经常重新安排的和弦进步上组成的。由于重新捕获可以引入广泛的变化，因此检测障碍是一项艰巨的任务。本文开发了一种新颖的矢量空间模型来表示和弦进展，并将其用于逆向检测。该过程适用音乐理论的原理，以减少和弦空间的维度，确定一个共同的钥匙签名表示并计算和弦共发生矩阵。矩阵的行构成了矢量空间的基础，在该矢量空间中，和弦进展表示为分段线性函数，并通过计算膜区域（一种新型的距离度量标准）来评估谐波相似性。为了说明我们的方法的有效性，我们将其应用于2,612个和弦进展的裁员语料库，并提供了示例，证明了其解释重新审判并找到相关性的能力。

制定了具有机器学习模拟（骆驼）项目的宇宙学和天体物理学，通过数千名宇宙的流体动力模拟和机器学习将宇宙学与天体物理学结合起来。骆驼包含4,233个宇宙学仿真，2,049个n-body和2,184个最先进的流体动力模拟，在参数空间中采样巨大的体积。在本文中，我们介绍了骆驼公共数据发布，描述了骆驼模拟的特性和由它们产生的各种数据产品，包括光环，次麦，银河系和空隙目录，功率谱，Bispectra，Lyman - $ \ Alpha $光谱，概率分布函数，光环径向轮廓和X射线光子列表。我们还释放了超过骆驼 - 山姆的数十亿个星系的目录：与Santa Cruz半分析模型相结合的大量N身体模拟。我们释放包含350多个Terabytes的所有数据，并包含143,922个快照，数百万光环，星系和摘要统计数据。我们提供有关如何访问，下载，读取和处理数据AT \ URL {https://camels.readthedocs.io}的进一步技术详细信息。