Anytime Neural Prediction via Slicing Networks Vertically

Understand

The pioneer deep neural networks (DNNs) have emerged to be deeper or wider for improving their accuracy in various applications of artificial intelligence.

• However, DNNs are often too heavy to deploy in practice, and it is often required to control their architectures dynamically given computing resource budget, i.e., anytime prediction.
• While most existing approaches have focused on training multiple shallow sub-networks jointly, we study training thin sub-networks instead.
• To this end, we first build many inclusive thin sub-networks (of the same depth) under a minor modification of existing multi-branch DNNs, and found that they can significantly outperform the state-of-art dense architecture for anytime prediction.