Titlebook: Neural Information Processing; 23rd International C Akira Hirose,Seiichi Ozawa,Derong Liu Conference proceedings 2016 Springer Internationa

不發(fā)音

管理員

dragon

MANIA

Conference proceedings 2016ion Processing, ICONIP 2016, held in Kyoto, Japan, in October 2016. The 296 full papers presented were carefully reviewed and selected from 431 submissions. The 4 volumes are organized in topical sections on deep and reinforcement learning; big data analysis; neural data analysis; robotics and contr

Prostatism

An Entropy Estimator Based on Polynomial Regression with Poisson Error Structureion. The density estimates at every given data points are averaged to obtain entropy estimators. The proposed estimator is shown to perform well through numerical experiments for various probability distributions.

goodwill

BPSpike II: A New Backpropagation Learning Algorithm for Spiking Neural Networksntees convergence to minimum error point, and unlike SpikeProp and its extensions, does not need a one-to-one correspondence between actual and desired spikes in advance. So, it is stably and widely applicable to practical problems.

彈藥

Gram-Schmidt Orthonormalization to the Adaptive ICA Function for Fixing the Permutation Ambiguity of AIF. The proposed method is theoretically guaranteed to extract the independent components in the unique order of the degree of non-Gaussianity. Consequently, it enables us to fix the permutation ambiguity. Experimental results on blind image separation problems show the usefulness of the proposed method.

Yag-Capsulotomy

Kernel L1-Minimization: Application to Kernel Sparse Representation Based Classificationice, ..-minimization is a better approach compared to OMP. The standard ..-minimization is a solved problem. For the first time in this work, we propose a technique for Kernel ..-minimization. Through simulation results we show that our proposed method outperforms prior kernelised greedy sparse recovery techniques.

Proponent

Non-parametric ,-mixture of Density Functionses. There are two typical mixtures in the context of information geometry, the .- and .-mixtures. This paper proposes a novel framework of non-parametric .-mixture modeling by using a simple estimation algorithm based on geometrical insights into the characteristics of the .-mixture. An experimental

參考書(shū)目