Ternary neural networks for resource-efficient AI applications

@article{Alemdar2017TernaryNN,
  title={Ternary neural networks for resource-efficient AI applications},
  author={Hande Alemdar and Vincent Leroy and Adrien Prost-Boucle and Fr{\'e}d{\'e}ric P{\'e}trot},
  journal={2017 International Joint Conference on Neural Networks (IJCNN)},
  year={2017},
  pages={2547-2554}
}
The computation and storage requirements for Deep Neural Networks (DNNs) are usually high. This issue limits their deployability on ubiquitous computing devices such as smart phones, wearables and autonomous drones. In this paper, we propose ternary neural networks (TNNs) in order to make deep learning more resource-efficient. We train these TNNs using a teacher-student approach based on a novel, layer-wise greedy methodology. Thanks to our two-stage training procedure, the teacher network is… CONTINUE READING
Highly Cited
This paper has 49 citations. REVIEW CITATIONS

Citations

Publications citing this paper.
Showing 1-10 of 32 extracted citations

References

Publications referenced by this paper.
Showing 1-10 of 29 references

C

  • S. K. Esser, P. A. Merolla, +7 authors D. R. Barch
  • di Nolfo, P. Datta, A. Amir, B. Taba, M. D…
  • 2016
Highly Influential
8 Excerpts

Similar Papers

Loading similar papers…