𝔖 Bobbio Scriptorium
✦   LIBER   ✦

The relative order and inverses of recurrent networks

✍ Scribed by C. Kambhampati; S. Manchanda; A. Delgado; G.G.R. Green; K. Warwick; M.T. Tham

Publisher
Elsevier Science
Year
1996
Tongue
English
Weight
764 KB
Volume
32
Category
Article
ISSN
0005-1098

No coin nor oath required. For personal study only.

✦ Synopsis

Differential geometry is used to investigate the structure of neural-network-based control systems. The key aspect is relative order-an invariant property of dynamic systems. Finite relative order allows the specification of a minimal architecture for a recurrent network. Any system with finite relative order has a left inverse. It is shown that a recurrent network with finite relative order has a local inverse that is also a recurrent network with the same weights. The results have implications for the use of recurrent networks in the inverse-model-based control of nonlinear systems.

πŸ“œ SIMILAR VOLUMES

Inverse optimal noise-to-state stabiliza
Inverse optimal noise-to-state stabilization of stochastic recurrent neural networks driven by noise of unknown covariance
✍ Ziqian Liu; Qunjing Wang; Henri Schurz πŸ“‚ Article πŸ“… 2009 πŸ› John Wiley and Sons 🌐 English βš– 173 KB

## Abstract In this paper, we extend our previous research results regarding the stabilization of recurrent neural networks from the concept of input‐to‐state stability to noise‐to‐state stability, and present a new approach to achieve noise‐to‐state stabilization in probability for stochastic recu