Abstract: The choice of activation function in deep learning is crucial to the performance of neural networks. The activation function used in conventional deep learning remains unchanged for neural ...
Abstract: Trust region (TR) and adaptive regularization using cubics (ARC) have proven to have some very appealing theoretical properties for nonconvex optimization by concurrently computing function ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results
Feedback