We explore the feasibility of Terrestrial Broadcasting in a Single-Frequency Network (SFN) with standard 5G New Radio (5GNR) numerology designed for uni-cast transmission. Instead classical OFDM symbol-by-symbol detector scheme or more complex equalization technique, we Recurrent-Neural-Network (RNN)-based that replaces channel estimation and blocks. The RNN is bidirectional Long Short-Term Mem...

Neural network has good nonlinear function approximation ability. It can be widely used to identify the model of controlled plant. In this chapter, the theories of modeling uncertain plant by using two kinds of neural networks: feed-forward neural network and recurrent neural network are introduced. And two adaptive control strategies for robotic tracking control are developed. One is recurrent...

We define directional recurrence for infinite measure preserving Z actions both intrinsically and via the unit suspension flow and prove that the two definitions are equivalent. We study the structure of the set of recurrent directions and show it is always a Gδ set. We construct an example of a recurrent action with no recurrent directions, answering a question posed in a 2007 paper of Daniel ...

Gain modulation is an important mechanism by which attentional and other inputs modify the amplitude of neuronal responses without changing their selectivity. Gain modulation has been studied previously in feedforward circuits but not in recurrent neural networks. We show how gain modulation modi"es the response of a recurrent network to feedforward inputs. Even modest gain modulation of the re...

In the context of sequence processing, we study the relationship between single-layer feedforward neural networks, that have simultaneous access to all items composing a sequence, and single-layer recurrent neural networks which access information one step at a time. We treat both linear and nonlinear networks, describing a constructive procedure, based on linear autoencoders for sequences, tha...

Abstract A class of recurrent neural networks is developed to solve nonlinear equations, which are approximated by a multilayer perceptron (MLP). The recurrent network includes a linear Hopfield network (LHN) and the MLP as building blocks. This network inverts the original MLP using constrained linear optimization and Newton’s method for nonlinear systems. The solution of a nonlinear equation ...

A method for storing sequences of varying lengths in a fixed-width vector is described. The method is implemented, in an adaptive form, in a recurrent network which learns to generate sequences. The performance of this network is compared with that of a more conventional recurrent network on the same task.

Complex neural dynamics produced by the recurrent architecture of neocortical circuits is critical to the cortex's computational power. However, the synaptic learning rules underlying the creation of stable propagation and reproducible neural trajectories within recurrent networks are not understood. Here, we examined synaptic learning rules with the goal of creating recurrent networks in which...