However, existing approaches either rely on the systems’ time dynamics, which requires sequential data processing and therefore hinders parallel computation 5, 6, 8, or employ large materials systems that are difficult to scale up 7. A promising approach is to exploit physical materials systems that perform this nonlinear projection intrinsically, because of their high computational density 5, inherent parallelism and energy efficiency 6, 7. Such nonlinear projections are computationally expensive in conventional computers.
In machine learning, nonlinear projection into a high-dimensional feature space can make data linearly separable 3, 4, simplifying the classification of complex features. Classification is an important task at which both biological and artificial neural networks excel 1, 2.
0 kommentar(er)
