Arm Community
Arm Community
  • Site
  • User
  • Site
  • Search
  • User
  • Groups
    • Arm Research
    • DesignStart
    • Education Hub
    • Graphics and Gaming
    • High Performance Computing
    • Innovation
    • Multimedia
    • Open Source Software and Platforms
    • Physical
    • Processors
    • Security
    • System
    • Software Tools
    • TrustZone for Armv8-M
    • 中文社区
  • Blog
    • Artificial Intelligence
    • Automotive
    • Healthcare
    • HPC
    • Infrastructure
    • Innovation
    • Internet of Things
    • Machine Learning
    • Mobile
    • Smart Homes
    • Wearables
  • Forums
    • All developer forums
    • IP Product forums
    • Tool & Software forums
    • Pelion IoT Platform
  • Activity
  • Support
    • Open a support case
    • Documentation
    • Downloads
    • Training
    • Arm Approved program
    • Arm Design Reviews
  • More
  • Cancel
Arm Research
  • Developer Community
  • Jump...
Arm Research
  • Research Articles
  • Resources
  • Events
  • About
  • Jump...
  • Cancel
  • New
  • All tags
  • Neural Network
  • ARM Accelerator
  • Arm Careers
  • Arm Research
  • Augmented Reality (AR)
  • Internet of Things (IoT)
  • machine learning
  • Machine Learning (ML)
  • mobile
  • Skipping RNN State-updates Without Retraining the Original Model

    Urmish Thakker
    Urmish Thakker

    Recurrent Neural Networks (RNNs) are an important class of algorithms. They are used in tasks where the strict order of the input conveys certain information, for example, natural language processing (NLP) and time-series based data. Increasingly, these…

    • 6 months ago
    • Arm Research
    • Research Articles
  • Alpha-Blending: Quantizing networks without using the STE

    Matthew Mattina
    Matthew Mattina

    Increasingly, intelligent applications are using neural networks at their core to deliver new functionality to users. These applications include language understanding and translation, image recognition, and object tracking and localization. Furthermore…

    • 10 months ago
    • Arm Research
    • Research Articles
  • Taking Constrained ML to the Next Level

    Charlotte Christopherson
    Charlotte Christopherson

    The Arm ML Research Lab explores cutting edge techniques and state-of-the-art algorithms. One of our primary research thrusts is investigating ways to bring more machine learning applications to Arm's products, and make existing applications more efficient

    …
    • 10 months ago
    • Arm Research
    • Research Articles
  • Learning low-precision neural networks without Straight-Through Estimator(STE)

    Charlotte Christopherson
    Charlotte Christopherson
    Zhi-Gang Liu, Matthew Mattina
    The Straight-Through Estimator (STE) is widely used for back-propagating gradients through the quantization function, but the STE technique lacks a complete theoretical understanding. We propose an alternative methodology…
    • Learning low-precision neural networks without Straight-Through Estimator(STE).pdf
    • over 1 year ago
    • Arm Research
    • Resources
  • Measuring scheduling efficiency of RNNs for NLP applications

    Charlotte Christopherson
    Charlotte Christopherson
    Urmish Thakker, Ganesh Dasika, Jesse Beu, Matthew Mattina
    Recurrent neural networks (RNNs) have shown state of the art results for speech recognition, natural language processing, image captioning and video summarizing applications. Many of these applications…
    • Measuring scheduling efficiency of RNNs for NLP applications.pdf
    • over 1 year ago
    • Arm Research
    • Resources
  • Ternary Hybrid Neural-Tree Networks for Highly Constrained IoT Applications

    Charlotte Christopherson
    Charlotte Christopherson
    Dibakar Gope, Ganesh Dasika, Matthew Mattina
    Machine learning-based applications are increasingly prevalent in IoT devices. The power and storage constraints of these devices make it particularly challenging to run modern neural networks, limiting the…
    • Ternary Hybrid Neural-Tree Networks for Highly Constrained IoT Applications.pdf
    • over 1 year ago
    • Arm Research
    • Resources
  • Efficient Hardware for Mobile Computer Vision via Transfer Learning

    Paul Whatmough
    Paul Whatmough

    Mobile computing is on the rise, and currently moving into some really exciting new applications and form factors ­– augmented reality (AR) glasses, unmanned aerial vehicles (UAVs), automated driver assistance systems (ADAS) in automobiles, and more.…

    • over 1 year ago
    • Arm Research
    • Research Articles
  • Arm ML Research Enables Augmented Reality Mobile Apps through Low-Power Machine Learning

    Paul Whatmough
    Paul Whatmough

    Augmented reality (AR) is a technology where virtual content is overlaid on top of the real world. If you’ve ever played with Snapchat “Lenses” on your mobile phone, to transform a selfie with a cartoon monocle or dog ears, you will…

    • over 2 years ago
    • Arm Research
    • Research Articles
  • View related content from anywhere
  • More
  • Cancel