Differentiable neural computers extend artificial neural networks with an explicit memory without interference, thus enabling the model to perform classic computation tasks such as graph traversal. However, such models are difficult to train, requiring long training times and large datasets. In this work, we achieve some of the computational capabilities of differentiable neural computers with a model that can be trained very efficiently, namely an echo state network with an explicit memory without interference. This extension enables echo state networks to recognize all regular languages, including those that contractive echo state networks provably can not recognize. Further, we demonstrate experimentally that our model performs comparably to its fully-trained deep version on several typical benchmark tasks for differentiable neural computers.
- Pub Date:
- September 2020
- Computer Science - Machine Learning;
- Computer Science - Neural and Evolutionary Computing;
- Statistics - Machine Learning
- In print at the special issue 'New Frontiers in Extremely Efficient Reservoir Computing' of IEEE TNNLS