Showing papers in "Neural Networks in 2016"

TL;DR: Using Laplace transform, the generalized Gronwall's inequality, Mittag-Leffler functions and linear feedback control technique, some new sufficient conditions are derived to ensure the finite-time synchronization of addressing FMNNs with fractional order α:1< α<2 and 0<α<1.

TL;DR: By means of linear delay feedback control and a fractional-order inequality, sufficient conditions are obtained to guarantee the synchronization of the drive-response systems.

TL;DR: Extensive experiments on handwritten digit classification, landmark recognition and face recognition demonstrate that the proposed hybrid classifier outperforms ELM and SRC in classification accuracy with outstanding computational efficiency.

TL;DR: Several sufficient conditions in complex-valued linear matrix inequality form are obtained to ensure the existence, uniqueness and global exponential stability of equilibrium point for the considered neural networks.

TL;DR: This paper is concerned with global exponential stability problem for a class of neural networks with time-varying delays using a new proposed inequality called free-matrix-based integral inequality, which is expressed by linear matrix inequalities.

TL;DR: This paper investigates the stability problem for a class of impulsive complex-valued neural networks with both asynchronous time-varying and continuously distributed delays by employing the idea of vector Lyapunov function, M-matrix theory and inequality technique to ensure the global exponential stability of equilibrium point.

TL;DR: The fixed-time master-slave synchronization of Cohen-Grossberg neural networks with parameter uncertainties and time-varying delays is investigated and a novel synchronization control strategy for the slave neural network is proposed.

TL;DR: The proposed results proved that the error system is globally asymptotically stable in the mean square and the criteria which ensure the synchronization between the uncontrolled system and controlled system are established through designed feedback controllers and linear matrix inequalities.

TL;DR: The problem of exponential stabilization and synchronization for fuzzy model of memristive neural networks (MNNs) is investigated by using periodically intermittent control with novel and useful stabilization criteria and synchronization conditions derived by using Lyapunov functional and differential inequality techniques.

TL;DR: By modeling the switching of network topologies as a Markov process, a novel event-triggered synchronization strategy is proposed and a sufficient condition for the mean square synchronization of the complex networks subject to Markovian switching topologies is established.

TL;DR: In this paper, the authors describe a new type of evolving connectionist systems (ECOS) called evolving spatio-temporal data machines based on neuromorphic, brain-like information processing principles (eSTDM).

TL;DR: By discussing ṫ(V)=μ(-1)(V), a general approach is provided to reveal the essence of finite-time stability and fixed-time convergence for the system V̇(t)=μ(V(t)).

TL;DR: This paper formulate and investigate the mixed H∞ and passivity based synchronization criteria for memristor-based recurrent neural networks with time-varying delays and the effectiveness of the proposed criterion is demonstrated through numerical examples.

TL;DR: A new event-triggered sampled-data transmission strategy, where only local and event-triggering states are utilized to update the broadcasting state of each agent, is proposed to realize cluster synchronization of the coupled neural networks.

TL;DR: The Noisy CNN algorithm speeds training on average because the backpropagation algorithm is a special case of the generalized expectation-maximization (EM) algorithm and because such carefully chosen noise always speeds up the EM algorithm on average.

TL;DR: The fault detection and isolation task achieved by using the residuals that are obtained from the dynamic ensemble scheme results in a significantly more accurate and reliable performance as illustrated through detailed quantitative confusion matrix analysis and comparative studies.

TL;DR: This paper presents an efficient hybrid feedback feedforward (HFF) adaptive approximation-based control (AAC) strategy for a class of uncertain Euler-Lagrange systems and guarantees a minimum configuration of the control structure and a minimum requirement of plant knowledge for the AAC design.

TL;DR: This paper proposes an algorithm based on the well-known Alternating Direction Method of Multipliers optimization procedure for a class of RNNs known as Echo State Networks, which compares favorably with a fully centralized implementation, in terms of speed, efficiency and generalization accuracy.

TL;DR: This paper investigates global projective synchronization of nonidentical fractional-order neural networks (FNNs) based on sliding mode control technique and designs a sliding mode controller to guarantee the occurrence of the sliding motion.

TL;DR: QPF is a direct generalization of a classical perceptron and solves some drawbacks found in previous models of quantum perceptrons, and SAL is the first learning algorithm to determine neural network architectures in polynomial time.

TL;DR: By means of matrix measure, generalized Halanay inequality, and matrix-norm inequality, several sufficient criteria for the global dissipativity of the addressed neural networks are proposed, and specific estimations of positive invariant sets and globally attractive sets are obtained.

TL;DR: The existence of global solution under the framework of Filippov for FNNDAs is proved by using a singular Gronwall inequality and the properties of fractional calculus.

TL;DR: A combination of the Lyapunov stability theory and the stochastic analysis technique is used to derive some easy-to-test conditions for the existence of the desired state estimator, which is characterized by the solution to a convex optimization problem that is solved via the semi-definite programme method.

TL;DR: Based on the geometrical properties of the discontinuous activation functions and the Brouwer's fixed point theory, the multistability issue is tackled for the complex-valued neural networks with discontinuousactivation functions and time-varying delays.

TL;DR: In MOS-ELM, meta-cognition is used to self-regulate the learning by selecting suitable learning strategies for class imbalance and concept drift problems, and a new adaptive window approach is proposed for concept drift learning.

TL;DR: The theory clarifies the concept of Hebbian learning, establishes the power and limitations of local learning rules, introduces the learning channel which enables a formal analysis of the optimality of backpropagation, and explains the sparsity of the space of learning rules discovered so far.

TL;DR: In this paper, a feed-forward neural network can be trained on the vector-field representation of a given dynamical system using backpropagation, then recast as a recurrent network that replicates the original system's dynamics.

TL;DR: Under the framework of Filippov solutions, boundedness and ultimate boundedness of solutions of memristor-based BAM neural networks are guaranteed by Chain rule and inequalities technique and a new method involving Yoshizawa-like theorem is favorably employed to acquire the existence of periodic solution.

TL;DR: This work presents a systematic and comprehensive approach for optimally handling regression tasks with very large high dimensional data by using smart sampling techniques for minimizing the number of samples to be generated by using an iterative approach that creates new sample sets until the input and output space of the function to be approximated are optimally covered.