Chaotic neural network applied to two-dimensional motion control

Abstract

Chaotic dynamics generated in a chaotic neural network model are applied to 2-dimensional (2-D) motion control. The change of position of a moving object in each control time step is determined by a motion function which is calculated from the firing activity of the chaotic neural network. Prototype attractors which correspond to simple motions of the object toward four directions in 2-D space are embedded in the neural network model by designing synaptic connection strengths. Chaotic dynamics introduced by changing system parameters sample intermediate points in the high-dimensional state space between the embedded attractors, resulting in motion in various directions. By means of adaptive switching of the system parameters between a chaotic regime and an attractor regime, the object is able to reach a target in a 2-D maze. In computer experiments, the success rate of this method over many trials not only shows better performance than that of stochastic random pattern generators but also shows that chaotic dynamics can be useful for realizing robust, adaptive and complex control function with simple rules.

Non-fragile synchronization of memristive BAM networks with random feedback gain fluctuations

“…Chaotic synchronization means the states of the connected systems are coincide each other, that is, it is a method to synchronize two identical chaotic systems (drive-response concept) with different initial conditions. Chaotic signal is conjectured to be used in communication schemes because of its inherent wide band characteristic, as a result, many synchronization methods work has been carried out for chaotic neural networks with time delays [23], [24], [25], [26], [27], [28], [29], [30]. The problem of synchronization of chaotic systems with randomly occurring uncertainties via stochastic sampled-data control has been investigated in [31].…”

Combined effects of LTP/LTD and synaptic scaling in formation of discrete and line attractors with persistent activity from non-trivial baseline

“…Here, these patterns can result from the intrinsic dynamics in local populations of neurons. Chaotic patterns of activity can be exploited to achieve motor tasks such as motion control (Yoshida et al 2010) and tracking (Li and Nara 2008).…”

Deterministic convergence of chaos injection-based gradient method for training feedforward neural networks

“…Besides the independent and identically distributed (i.i.d) noises, chaos noise is also widely used and has been shown to be effective (Ahmed et al 2011;Uwate et al 2004) when injected into the gradient training process of feedforward neural networks. Chaos injection enhances the resemblance to biological systems (Li and Nara 2008;Yoshida et al 2010), and the dynamic variation that it introduces facilitates escaping from local minima and thus improves the convergence (Ahmed et al 2011). However, as the chaos is not an i.i.d variable, the existing convergence results and the corresponding analysis methods for noise injectionbased online gradient methods can not be directly applied to the chaos injection-based gradient methods (CIBGM).…”