Obtaining the Puiseux series of multiple imaginary (characteristic) roots (MIRs) is a fundamental issue in the stability analysis of time-delay systems. However, to the best of the authors' knowledge, this issue has not been fully investigated up to date. This note focuses on the Puiseux series expansion of MIRs of linear time-invariant systems including commensurate delays. For an MIR of any multiplicity, we propose an algorithm for defining the structure of the Puiseux series, as well as the explicit computation of the corresponding coefficients. By using the proposed method, we can find all the Puiseux series corresponding to all the root loci.

The coexistence of multiple stable equilibria in recurrent neural networks is an important dynamic characteristic for associative memory and other applications. In this paper, the existence and local Mittag-Leffler stability of multiple equilibria are investigated for a class of fractional-order recurrent neural networks with discontinuous and nonmonotonic activation functions. By using Brouwer $^{\prime }\text{s}$ fixed point theory, several conditions are established to ensure the existence of $5^{n}$ equilibria, in which all the components of $4^{n}$ equilibria are located in the continuous intervals of the activation functions. and some of the components of $5^{n}-4^{n}$ equilibria are located at some discontinuous points of the activation functions. The introduction of discontinuous activation functions makes the neural networks have more equilibria than those with continuous activation functions. Furthermore, some criteria are proposed to ensure local Mittag-Leffler stability of $3^{n}$ equilibria. The introduction of nonmonotonic activation functions makes the neural networks have more stable equilibria than those with monotonic activation functions. Two examples are given to illustrate the effectiveness of the results.

In this paper, a nearly data-based optimal control scheme is proposed for linear discrete model-free systems with delays. The nearly optimal control can be obtained using only measured input/output data from systems, by reinforcement learning technology, which combines Q-learning with value iterative algorithm. First, we construct a state estimator by using the measured input/output data. Second, the quadratic functional is used to approximate the value function at each point in the state space, and the data-based control is designed by Q-learning method using the obtained state estimator. Then, the paper states the method, that is, how to solve the optimal inner kernel matrix $\bar{P}$ in the least-square sense, by value iteration algorithm. Finally, the numerical examples are given to illustrate the effectiveness of our approach.