Bo Liu

TL;DR: A sign-bi-power activation function is proposed in this paper to accelerate Zhang neural network to finite-time convergence and the proposed strategy is applied to online calculating the pseudo-inverse of a matrix and nonlinear control of an inverted pendulum system.

TL;DR: The global stability of the proposed neural network and the optimality of the neural solution are proven in theory and application orientated simulations demonstrate the effectiveness of this proposed method.

TL;DR: Theoretical analysis of gradient TD (GTD) reinforcement learning methods implies that the GTD family of algorithms are comparable and may indeed be preferred over existing least squares TD methods for off-policy learning, due to their linear complexity.

TL;DR: The authors derived primal-dual saddle-point objective functions to obtain finite-sample bounds on the performance of gradient TD (GTD) reinforcement learning methods and showed that the results imply that the GTD family of algorithms are comparable and may indeed be preferred over existing least squares TD methods for off-policy learning, due to their linear complexity.

TL;DR: This paper presents a simple model, which produces the WTA competition by taking advantage of selective positive-negative feedback through the interaction of neurons via p-norm, and has an explicit explanation of the competition mechanism.