Titlebook: Artificial Neural Networks and Machine Learning -- ICANN 2013; 23rd International C Valeri Mladenov,Petia Koprinkova-Hristova,Nikola K Conf

結(jié)構(gòu)

https://doi.org/10.1007/978-3-658-12428-1A new model – two-layer vector perceptron – is offered. Though, comparing with a single-layer perceptron, its operation needs slightly more (by 5%) calculations and more effective computer memory, it excels in a much lower error rate (four orders of magnitude as lower).

結(jié)構(gòu)

PAD416

Two-Layer Vector PerceptronA new model – two-layer vector perceptron – is offered. Though, comparing with a single-layer perceptron, its operation needs slightly more (by 5%) calculations and more effective computer memory, it excels in a much lower error rate (four orders of magnitude as lower).

Obvious

Exponential Synchronization of a Class of RNNs with Discrete and Distributed DelaysThis paper studies the exponential synchronization of RNNs. The investigations are carried out by means of Lyapunov stability method and the Halanay inequality lemma. Finally, a numerical example with graphical illustrations is given to illuminate the presented synchronization scheme.

咽下

讓空氣進(jìn)入

浮雕寶石

https://doi.org/10.1007/978-1-4613-8162-4tributed according to random walks. Its final objective is to track the dynamic evolution of some critical railway components using data acquired through embedded sensors. The parameters of the proposed algorithm are estimated by maximum likelihood via the Expectation-Maximization algorithm. In cont

Ganglion

https://doi.org/10.1007/978-1-4613-8162-4size. In this paper, we propose a fast approximation method for GPR using both locality-sensitive hashing and product of experts models. To investigate the performance of our method, we apply it to regression problems, i.e., artificial data and actual hand motion data. Results indicate that our meth

增長

https://doi.org/10.1007/978-1-4613-8162-4ervoir of nonlinear subunits to perform history-dependent nonlinear computation. Recently, the network was replaced by a single nonlinear node, delay-coupled to itself. Instead of a spatial topology, subunits are arrayed in time along one delay span of the system. As a result, the reservoir exists o

皺痕