论文标题
储层内存机
Reservoir memory machines
论文作者
论文摘要
近年来，神经图灵机通过将神经网络的灵活性与图灵机的计算能力相连，从而引起了人们的注意。但是，众所周知，神经图灵机很难训练，这限制了其适用性。我们提出了储层存储器，该机器仍然能够解决神经图灵机的一些基准测试，但训练速度要快得多，只需要对齐算法和线性回归。我们的模型也可以看作是具有外部内存的回声状态网络的扩展，可以随意存储而无需干扰。
In recent years, Neural Turing Machines have gathered attention by joining the flexibility of neural networks with the computational capabilities of Turing machines. However, Neural Turing Machines are notoriously hard to train, which limits their applicability. We propose reservoir memory machines, which are still able to solve some of the benchmark tests for Neural Turing Machines, but are much faster to train, requiring only an alignment algorithm and linear regression. Our model can also be seen as an extension of echo state networks with an external memory, enabling arbitrarily long storage without interference.
