Alternating optimization method based on nonnegative matrix factorizations for deep neural networks

Preprint English OPEN
Sakurai, Tetsuya; Imakura, Akira; Inoue, Yuto; Futamura, Yasunori;
  • Subject: Statistics - Machine Learning | Computer Science - Neural and Evolutionary Computing | Computer Science - Learning
    arxiv: Computer Science::Neural and Evolutionary Computation

The backpropagation algorithm for calculating gradients has been widely used in computation of weights for deep neural networks (DNNs). This method requires derivatives of objective functions and has some difficulties finding appropriate parameters such as learning rate... View more
Share - Bookmark