Adding Filters to Improve Reservoir Computer Performance
This work addresses a practical problem for researchers and engineers building neuromorphic computers by offering an incremental improvement to enhance performance with simpler hardware implementation.
The paper tackled the challenge of improving reservoir computer performance by adding linear filters to the output, which are easier to implement than complex node connections. The result showed simulated performance gains in signal fitting, prediction, and classification tasks, though no concrete numbers were provided.
Reservoir computers are a type of neuromorphic computer that may be built a an analog system, potentially creating powerful computers that are small, light and consume little power. Typically a reservoir computer is build by connecting together a set of nonlinear nodes into a network; connecting the nonlinear nodes may be difficult or expensive, however. This work shows how a reservoir computer may be expanded by adding functions to its output. The particular functions described here are linear filters, but other functions are possible. The design and construction of linear filters is well known, and such filters may be easily implemented in hardware such as field programmable gate arrays (FPGA's). The effect of adding filters on the reservoir computer performance is simulated for a signal fitting problem, a prediction problem and a signal classification problem.