The lack of interpretability remains a key barrier to the adoption of deep models in many
applications. In this work, we explicitly regularize deep models so human users might step …

Abstract Bayesian Neural Networks (BNNs) have recently received increasing attention for
their ability to provide well-calibrated posterior uncertainties. However, model selection …

The promise of augmenting accurate predictions provided by modern neural networks with
well-calibrated predictive uncertainties has reinvigorated interest in Bayesian neural …

Bayesian Neural Networks (BNNs) have recently received increasing attention for their
ability to provide well-calibrated posterior uncertainties. However, model selection---even …

A smooth group regularization method is proposed to identify and remove the redundant
input nodes of feedforward neural networks, or equivalently the redundant dimensions of the …

Feature reduction is nowadays an important topic in machine learning as it reduces the
complexity of the final model and makes it easier to interpret. In some applications, the …

Network complexity and computational efficiency have become increasingly significant
aspects of deep learning. Sparse deep learning addresses these challenges by recovering …

Deep models have advanced prediction in many domains, but their lack of interpretability
remains a key barrier to the adoption in many real world applications. There exists a large …

Network complexity and computational efficiency have become increasingly significant
aspects of deep learning. Sparse deep learning addresses these challenges by recovering …

A group L 1/2 regularization term is defined and introduced into the conventional error
function for pruning the hidden layer nodes of feedforward neural networks. This group L 1/2 …