Conditional Deep Learning for energy-efficient and enhanced pattern recognition

@article{Panda2016ConditionalDL,
  title={Conditional Deep Learning for energy-efficient and enhanced pattern recognition},
  author={Priyadarshini Panda and Abhronil Sengupta and Kaushik Roy},
  journal={2016 Design, Automation & Test in Europe Conference & Exhibition (DATE)},
  year={2016},
  pages={475-480}
}
Deep learning neural networks have emerged as one of the most powerful classification tools for vision related applications. However, the computational and energy requirements associated with such deep nets can be quite high, and hence their energy-efficient implementation is of great interest. Although traditionally the entire network is utilized for the recognition of all inputs, we observe that the classification difficulty varies widely across inputs in real-world datasets; only a small… CONTINUE READING
Tweets
This paper has been referenced on Twitter 10 times. VIEW TWEETS

Figures, Tables, Results, and Topics from this paper.

Key Quantitative Results

  • In addition, our results show an improvement in classification accuracy from 97.5% to 98.9% as compared to the original network.

Citations

Publications citing this paper.
SHOWING 1-10 OF 20 CITATIONS

References

Publications referenced by this paper.
SHOWING 1-10 OF 16 REFERENCES

Spintronic deep learning engine for large-scale neuromorphic computing

  • In Proceedings of the international symposium on…
  • 2014
1 Excerpt

Similar Papers

Loading similar papers…