Dimension reduction in recurrent networks by canonicalization

• المؤلفون الرئيسيون: Grigoryeva, Lyudmila, Ortega, Juan-Pablo
• مؤلفون آخرون: School of Physical and Mathematical Sciences
• التنسيق: مقال
• اللغة: English
• منشور في: 2022
• الموضوعات: Science::Mathematics; Recurrent Neural Network; Reservoir Computing
• الوصول للمادة أونلاين: https://hdl.handle.net/10356/161577

Many recurrent neural network machine learning paradigms can be formulated using state-space representations. The classical notion of canonical state-space realization is adapted in this paper to accommodate semi-infinite inputs so that it can be used as a dimension reduction tool in the recurrent n...