A framework for parameter estimation and model selection in kernel deep stacking networks
Conclusions KDSNs are a computationally efficient appoximation of backpropagation-based artificial neural network techniques. Application of the proposed methodology results in a fast tuning procedure that generates KDSN fits having a similar prediction accuracy as other techniques in the field of deep learning.
Source: Artificial Intelligence in Medicine - Category: Bioinformatics Source Type: research
More News: Bioinformatics | Diabetes | Endocrinology | Learning | Statistics | Study | Universities & Medical Training