Build a compact binary neural network through bit-level sensitivity and data pruning

Yixing Li, Shuai Zhang, Xichuan Zhou, Fengbo Ren

Research output: Contribution to journalArticlepeer-review

8 Scopus citations


Due to the high computational complexity and memory storage requirement, it is hard to directly deploy a full-precision convolutional neural network (CNN) on embedded devices. The hardware-friendly designs are needed for resource-limited and energy-constrained embedded devices. Emerging solutions are adopted for the neural network compression, e.g., binary/ternary weight network, pruned network and quantized network. Among them, binary neural network (BNN) is believed to be the most hardware-friendly framework due to its small network size and low computational complexity. No existing work has further shrunk the size of BNN. In this work, we explore the redundancy in BNN and build a compact BNN (CBNN) based on the bit-level sensitivity analysis and bit-level data pruning. The input data is converted to a high dimensional bit-sliced format. In the post-training stage, we analyze the impact of different bit slices to the accuracy. By pruning the redundant input bit slices and shrinking the network size, we are able to build a more compact BNN. Our result shows that we can further scale down the network size of the BNN up to 3.9x with no more than 1% accuracy drop. The actual runtime can be reduced up to 2x and 9.9x compared with the baseline BNN and its full-precision counterpart, respectively.

Original languageEnglish (US)
Pages (from-to)45-54
Number of pages10
StatePublished - Jul 20 2020


  • Binary neural networks
  • Deep learning
  • Deep neural networks
  • Neural network compression

ASJC Scopus subject areas

  • Computer Science Applications
  • Cognitive Neuroscience
  • Artificial Intelligence


Dive into the research topics of 'Build a compact binary neural network through bit-level sensitivity and data pruning'. Together they form a unique fingerprint.

Cite this