Search papers, labs, and topics across Lattice.
University of Zanjan, Zanjan, Iran
2
1
5
Quantizing neural networks doesn't have to mean sacrificing robustness: a new three-stage framework achieves up to 10.35% better attack resilience and 12.47% better fault resilience.
Forget exhaustive search: HAWX achieves up to 3 million times speedup in DNN approximation by intelligently integrating heterogeneous approximate computing blocks, guided by multi-level sensitivity analysis.
