EMEA 2021 Student Forum: Squeeze-and-Threshold based quantization forLow-Precision Neural Networks



EMEA 2021 Student Forum
Squeeze-and-Threshold based quantization forLow-Precision Neural Networks
Binyi WU, PhD Student, Infineon Technologies AG

Problem statement: Deep Convolutional Neural Networks (DCNNs), widely used for image recognition, require a large amount of calculation and memory, making them infeasible to run on embedded devices. Among various effective techniques such as quantization and pruning, 8-bit quantization is the most widely used method. However, it is not sufficient for embedded devices with extremely limited hardware resource. Prior work has already demonstrated lower precision quantization is feasible but they have different schemes on 1-bit and multi-bit quantization. In this work, we proposed a new quantization method based on attention mechanism, which unify the binarization and multi-bit quantization of activations into one and demonstrate state-of-the-art performance.
Relevance to tinyML: The proposed low-precision (1,2,3,4-bit) quantization method is a neural network optimization method for low-power application.
Novelty: 1. First time to apply attention mechanism on quantization 2. A consistent method on 1-bit and multi-bit quantization
Approach:
The floating-point convolution operation (left) is replaced with quantized convolution operation.

source

2 thoughts on “EMEA 2021 Student Forum: Squeeze-and-Threshold based quantization forLow-Precision Neural Networks

  • August 9, 2021 at 11:33 pm
    Permalink

    Best view i have ever seen !

    Reply
  • August 23, 2021 at 8:14 am
    Permalink

    Thank you for each of your work on this site. My aunt takes pleasure in getting into internet research and it is simple to grasp why. My partner and i know all relating to the powerful mode you produce vital suggestions by means of your website and as well boost participation from others about this area of interest then my princess is without question being taught a lot. Take advantage of the remaining portion of the new year. You’re the one doing a terrific job.

    Reply

Leave a Reply

Your email address will not be published.