Reservoir computing for spatiotemporal signal classification without trained output weights
This work addresses a specific bottleneck in reservoir computing for researchers and practitioners by offering a more efficient and robust method for signal classification, though it is incremental as it builds on existing paradigms.
The paper tackles the problem of simplifying reservoir computing for spatiotemporal signal classification by eliminating the need for trained output weights, proposing a supervised clustering method based on principal components of reservoir state norms. The result shows that this approach can outperform traditional methods in classification accuracy and parameter sensitivity, as demonstrated through numerical experiments on real-world data.
Reservoir computing is a recently introduced machine learning paradigm that has been shown to be well-suited for the processing of spatiotemporal data. Rather than training the network node connections and weights via backpropagation in traditional recurrent neural networks, reservoirs instead have fixed connections and weights among the `hidden layer' nodes, and traditionally only the weights to the output layer of neurons are trained using linear regression. We claim that for signal classification tasks one may forgo the weight training step entirely and instead use a simple supervised clustering method based upon principal components of norms of reservoir states. The proposed method is mathematically analyzed and explored through numerical experiments on real-world data. The examples demonstrate that the proposed may outperform the traditional trained output weight approach in terms of classification accuracy and sensitivity to reservoir parameters.