A Universal Compression Algorithm for Deep Neural Networks

  • Zoom

    * Register (or log in) to the Neural Network to add this session to your agenda or watch the replay

  • Date
    21 August 2020
    Timeframe
    13:00 - 14:00 CEST, Geneva
    Duration
    60 minutes
    Share this session

    In the past decade, deep neural networks (DNNs) have shown state-of-the-art performance on a wide range of complex machine learning tasks. Many of these results have been achieved while growing the size of DNNs, creating a demand for efficient compression and transmission of them. This talk will present DeepCABAC, a universal compression algorithm for DNNs that through its adaptive, context-based rate modeling, allows an optimal quantization and coding of neural network parameters. It compresses state-of-the-art DNNs up to 1.5% of their original size with no accuracy loss and has been selected as basic compression technology for the emerging MPEG-7 part 17 standard on DNN compression.