I think this is a necessary research direction for the reliable and widespread use of deep neural networks for critical applications. What are the current approaches to understand the optimization process inherent in the training of such networks?
The Apply AI Alliance is as a multi-stakeholder forum engaged in large discussion of all aspects of AI development and its impact on the economy and society.
I think this is a necessary research direction for the reliable and widespread use of deep neural networks for critical applications. What are the current approaches to understand the optimization process inherent in the training of such networks?