State of the Art in Compressing Deep Convolutional Neural Networks

Here at LeapMind we are working on making deep learning empowered intelligent IoT devices a widespread reality. One of the topics our R&D is most concerned about is the compression of deep learning models. In this blog post I would like to talk about why this is important and give an overview of the literature on this topic…

Nicolas Loerbroks’ full article on the “State of the Art in Compressing Deep Convolutional Neural Networks” can be found on the Medium platform.Please take a look: https://medium.com/@nicolas_19145/state-of-the-art-in-compressing-deep-convolutional-neural-networks-cfd8c5404f22

LeapMind株式会社では一緒に働く仲間を募集しています

松岡由香子

LeapMind株式会社 / 広報

DeepLearning LeapMind

2 いいね！

LeapMind株式会社

"機械学習を使った今までにないデバイスをあまねく世に広める"を企業理念に、独自のディープラーニングモデルの軽量化技術や専用回路設計技術と150を超える企業との共創で得た知見を活かし、事業を展開しています。私たちが開発したコア製品である”Efficiera"は、独自のディープラーニングモデル軽量化手法「極小量子化技術」を最大限に活かす、FPGAデバイス上もしくはASICデバイス上の回路として動作するCNNの推論演算処理に特化した超低消費電力AI推論アクセラレータIPで、今までAIが使えなかったような環境でもdeep learningによる高度な情報処理を可能にします。超低消費電力AIアクセラレータIP EFFICIERA https://leapmind.io/business/ip/ LeapMind Inc. is developing its business with the company mission, “to create innovative devices with machine learning and make them available everywhere” and our original weight reduction technology for deep learning models, the dedicated circuit design, and leveraging the knowledge gained from the collaboration with more than 150 companies. Our core product "Efficiera" is an ultra-low power AI inference accelerator that can be implemented on an FPGA device or ASIC/ASSP device, and is specialized for CNN inference operations, taking full advantage of our original deep learning model weight reduction method "extremely low bit quantization". It will enable advanced data processing by deep learning in environments where AI could not be used before. Ultra low power AI inference accelerator IP EFFICIERA https://leapmind.io/en/business/ip/