Quantization of deep neural networks for accumulator-constrained processors

Barry de Bruin (Corresponding author), Zoran Zivkovic, Henk Corporaal

Research output: Contribution to journalArticleAcademicpeer-review

2 Citations (Scopus)
2656 Downloads (Pure)


We introduce an Artificial Neural Network (ANN) quantization methodology for platforms without wide accumulation registers. This enables fixed-point model deployment on embedded compute platforms that are not specifically designed for large kernel computations (i.e. accumulator-constrained processors). We formulate the quantization problem as a function of accumulator size, and aim to maximize the model accuracy by maximizing bit width of input data and weights. To reduce the number of configurations to consider, only solutions that fully utilize the available accumulator bits are being tested. We demonstrate that 16 bit accumulators are able to obtain a classification accuracy within 1% of the floating-point baselines on the CIFAR-10 and ILSVRC2012 image classification benchmarks. Additionally, a near-optimal 2 × speedup is obtained on an ARM processor, by exploiting 16 bit accumulators for image classification on the All-CNN-C and AlexNet networks.

Original languageEnglish
Article number102872
Number of pages11
JournalMicroprocessors and Microsystems
Publication statusPublished - 1 Feb 2020


  • Convolutional neural networks
  • Efficient inference
  • Fixed-point
  • Narrow accumulators
  • Quantization


Dive into the research topics of 'Quantization of deep neural networks for accumulator-constrained processors'. Together they form a unique fingerprint.

Cite this