.png){kind=icon}
返回
A kernel-expanded stochastic neural network
.png){kind=icon}
OA
AI
DOI：10.1111/rssb.12496.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
The deep neural network suffers from many fundamental issues in machine learning. For example, it often gets trapped into a local minimum in training, and its prediction uncertainty is hard to be assessed. To address these issues, we propose the so-called kernel-expanded stochastic neural network (K-StoNet) model, which incorporates support vector regression as the first hidden layer and reformulates the neural network as a latent variable model. The former maps the input vector into an infinite dimensional feature space via a radial basis function kernel, ensuring the absence of local minima on its training loss surface. The latter breaks the high-dimensional non-convex neural network training problem into a series of low-dimensional convex optimization problems, and enables its prediction uncertainty easily assessed. The K-StoNet can be easily trained using the imputation-regularized optimization algorithm. Compared to traditional deep neural networks, K-StoNet possesses a theoretical guarantee to asymptotically converge to the global optimum and enables the prediction uncertainty easily assessed. The performances of the new model in training, prediction and uncertainty quantification are illustrated by simulated and real data examples.
Keyword:
global optimum
imputation-regularized optimization
latent variable model
support vector regression
uncertainty quantification
期刊
J
IF:
3.6
论文数:
1.5K
被引数:
3.2W
机构
引用论文
On the Development and Applications of Cellulosic Nanofibrillar and Nanocrystalline Materials纤维素纳米原纤和纳米晶材料的发展与应用
PREAI
分享收藏分享收藏Econometrics of Domestication of the African Palm Weevil (Rhynchophorus phoenicisF.) Production as Small-Scale Business in Ghana加纳作为小型企业生产非洲椰子象鼻虫（Rhynchophorus phoenicisF.）驯养的经济计量学
PREAI
分享收藏STATISTICAL CONSISTENCY AND ASYMPTOTIC NORMALITY FOR HIGH-DIMENSIONAL ROBUST M-ESTIMATORS高维鲁棒M-估计的统计一致性和渐近正态性.png)
ANNALS OF STATISTICS
OAAI
ANNALS OF STATISTICSIF3.7
OAAI分享收藏Crystal chemistry and metal-hydrogen bonding in anisotropic and interstitial hydrides of intermetallics of rare earth (R) and transition metals (T), RT3 and R2T7稀土 (R) 和过渡金属 (T) 的金属间化合物的各向异性和间隙氢化物中的晶体化学和金属氢键，RT3 和R2T7
PREAI
分享收藏
查看更多内容