Dynamic Representations Toward Efficient Inference on Deep Neural Networks by Decision Gates

no code implementations • 5 Nov 2018 • Mohammad Saeed Shafiee, Mohammad Javad Shafiee, Alexander Wong

The proposed d-gate modules can be integrated with any deep neural network and reduces the average computational cost of the deep neural networks while maintaining modeling accuracy.

Efficient Inference on Deep Neural Networks by Dynamic Representations and Decision Gates

no code implementations • NIPS Workshop CDNNRIA 2018 • Mohammad Saeed Shafiee, Mohammad Javad Shafiee, Alexander Wong

The current trade-off between depth and computational cost makes it difficult to adopt deep neural networks for many industrial applications, especially when computing power is limited.