Titlebook: Advances in Neural Networks - ISNN 2009; 6th International Sy Wen Yu,Haibo He,Nian Zhang Conference proceedings 2009 Springer-Verlag Berlin

Harbor

Observe & Assess Program Needs,ynomial interpolation and approximation theory, a special type of feedforward neural-network is constructed in this paper with hidden-layer neurons activated by Bernoulli polynomials. Different from conventional BP and gradient-based training algorithms, a weights-direct-determination (WDD) method i

COMMA

Observe

Operationalize the Evaluation Plan,ntrusion detection method based on workflow feature definition according to KDD cup 99 types with feed forward BP neural network. The workflow can define new attacks sequence to help BP neural network recognize new attacks. The method takes network traffic data to analyze and classify the behaviors

Creatinine-Test

https://doi.org/10.1007/978-0-387-77377-3in. In this article, a neuron described by Hodgkin-Huxley model receives periodic spike-train inputs. The responses to inputs with various frequencies and synaptic conductivities are simulated. The results show that mode-locking response pattern is the main type of response to periodic inputs, which

Abduct

https://doi.org/10.1007/978-0-387-77377-3he proposed algorithm combines two mechanisms to improve neural network’s performance. First, it introduces stochastic dynamics into the competitive Hopfield neural network (CHNN) to help the network escape from local minima. Second, it adopts multi-start strategy to further improve the performance

Affirm

Operationalize the Evaluation Plan,hich can be interpreted as an information theoretic formulation of the sparse coding. Viewing as an entropy minimization problem, the rate distortion theory and consequently the sparse coding are extended to discriminative variants. As a concrete example of this information theoretic sparse coding,

altruism

Factorable

hair-bulb

千篇一律

https://doi.org/10.1007/978-3-031-07446-2k. Even though the target function is unknown in advance, the learning error can be still acquired and then is utilized to determine whether the input space needs to be repartitioned or not. Once the input space is determined to be repartitioned, some new knots are inserted for further quantization,