Reservoir computing advances the intriguing idea that a nonlinear recurrent neural circuit-the reservoir-can encode spatio-temporal input signals to enable efficient ways to perform tasks like classification or regression. However, recently the idea of a monolithic reservoir network that simultaneously buffers input signals and expands them into nonlinear features has been challenged. A representation scheme in which memory buffer and expansion into higher-order polynomial features can be configured separately has been shown to significantly outperform traditional reservoir computing in prediction of multivariate time-series. Here we propose a configurable neuromorphic representation scheme that provides competitive performance on prediction, but with significantly better scaling properties than directly materializing higher-order features as in prior work. Our approach combines the use of randomized representations from traditional reservoir computing with mathematical principles for approximating polynomial kernels via such representations. While the memory buffer can be realized with standard reservoir networks, computing higher-order features requires networks of 'Sigma-Pi' neurons, i.e., neurons that enable both summation as well as multiplication of inputs. Finally, we provide an implementation of the memory buffer and Sigma-Pi networks on Loihi 2, an existing neuromorphic hardware platform.
2147640/NSF | NSF Office of the Director | Office of International Science and Engineering (Office of International Science & Engineering)
2313149/NSF | NSF Office of the Director | Office of International Science and Engineering (Office of International Science & Engineering)
R01-EB026955/Foundation for the National Institutes of Health (Foundation for the National Institutes of Health, Inc.)
IIS1718991/NSF | NSF Office of the Director | Office of International Science and Engineering (Office of International Science & Engineering)
R01 EB026955/NIBIB NIH HHS
839179/EC | EU Framework Programme for Research and Innovation H2020 | H2020 Priority Excellent Science | H2020 Marie Sk��odowska-Curie Actions (H2020 Excellent Science - Marie Sk��odowska-Curie Actions)
N/A/U.S. Department of Defense (United States Department of Defense)
