Two potential bottlenecks on the expressiveness of recurrent neural networks (RNNs) are their ability to store information about the task in their parameters, and to store information about the input history in their units. We show experimentally that all common RNN architectures achieve nearly the same per-task and per-unit capacity bounds with careful training, for a variety of tasks and stacking depths. They can store an amount of task information which is linear in the number of parameters, and is approximately 5 bits per parameter. They can additionally store approximately one real number from their input history per hidden unit. We further find that for several tasks it is the per-task parameter capacity bound that determines performance. These results suggest that many previous results comparing RNN architectures are driven primarily by differences in training effectiveness, rather than differences in capacity. Supporting this observation, we compare training difficulty for several architectures, and show that vanilla RNNs are far more difficult to train, yet have higher capacity. Finally, we propose two novel RNN architectures, one of which is easier to train than the LSTM or GRU.

通过实验证实了，所有常见的递归神经网络在仔细训练后达到了近乎相同的任务能力和单元容量边界，而许多以前的结果比较不同的递归神经网络结构主要是由于训练效果的差异而不是由于容量的差异驱动的。同时，作者还提出了两个新的递归神经网络结构，其中一个对于深度堆叠结构的训练比LSTM或GRU更容易。

循环神经网络的容量与可训练性