Titlebook: Neural Information Processing; 24th International C Derong Liu,Shengli Xie,El-Sayed M. El-Alfy Conference proceedings 2017 Springer Interna

ventilate

Improving Generalization Capability of Extreme Learning Machine with Synthetic Instances Generation of ELM with Synthetic Instances Generation (SIGELM). We focus on optimizing the output-layer weights via adding informative synthetic instances to the training dataset at each learning step. In order to get the required synthetic instances, a neighborhood is determined for each high-uncertainty tra

buoyant

Adaptive , , Regularization: Oracle Property and Applications sample size. Other than the case of the number of covariates is smaller than the sample size, in this paper, we prove that under appropriate conditions, these adaptive . estimators possess the oracle property in the case that the number of covariates is much larger than the sample size. We present

negotiable

難解

業(yè)余愛好者

圣人

Hybrid RVM Algorithm Based on the Prediction Variance solve nonlinear problems by using kernel functions. Biased wavelets are localized in time and infrequency but, unlike wavelets, have adjustable nonzero mean. The proposed hybrid algorithm employs a family of biased wavelets to construct the kernel functions of RVM, which makes the kernel of RVM mor

Nomadic

訓(xùn)誡

A Self-adaptive Growing Method for Training Compact RBF Networksrtional to the number of nodes in its hidden layer, while there is also a positive correlation between the number of nodes and the predication accuracy. In this paper, we propose a new training algorithm for RBF networks in order to construct high accuracy networks with as few nodes as possible. The

玷污

Incremental Extreme Learning Machine via Fast Random Search Methodo avoid this problem, enhanced random search based incremental extreme learning machine (EI-ELM) is proposed. However, we find that the EI-ELM’s training time is too long. In addition, EI-ELM can only add hidden nodes one by one. This paper proposes a fast method for EI-ELM (referred to as FI-ELM).

Wallow

Learning of Phase-Amplitude-Type Complex-Valued Neural Networks with Application to Signal Coherenceation functions, which can be applied to deal with coherent signals effectively. The performance of the proposed L-BFGS algorithm is compared with traditional complex-valued stochastic gradient descent method on the tasks of wave-related signal processing with various degrees of coherence. The exper