Tuesday, March 9, 2021
  • Setup menu at Appearance » Menus and assign menu to Top Bar Navigation
Advertisement
  • AI Development
    • Artificial Intelligence
    • Machine Learning
    • Neural Networks
    • Learn to Code
  • Data
    • Blockchain
    • Big Data
    • Data Science
  • IT Security
    • Internet Privacy
    • Internet Security
  • Marketing
    • Digital Marketing
    • Marketing Technology
  • Technology Companies
  • Crypto News
No Result
View All Result
NikolaNews
  • AI Development
    • Artificial Intelligence
    • Machine Learning
    • Neural Networks
    • Learn to Code
  • Data
    • Blockchain
    • Big Data
    • Data Science
  • IT Security
    • Internet Privacy
    • Internet Security
  • Marketing
    • Digital Marketing
    • Marketing Technology
  • Technology Companies
  • Crypto News
No Result
View All Result
NikolaNews
No Result
View All Result
Home Machine Learning

Google releases API to train smaller, faster AI models

April 9, 2020
in Machine Learning
Google releases API to train smaller, faster AI models
586
SHARES
3.3k
VIEWS
Share on FacebookShare on Twitter

Google today released Quantization Aware Training (QAT) API, which enables developers to train and deploy models with the performance benefits of quantization — the process of mapping input values from a large set to output values in a smaller set — while retaining close to their original accuracy. The goal is to support the development of smaller, faster, and more efficient machine learning models well-suited to run on off-the-shelf machines, such as those in medium- and small-business environments where computation resources are at a premium.

Often, the process of going from a higher to lower precision is noisy. That’s because quantization squeezes a small range of floating-point values into a fixed number of information buckets, leading to information loss similar to rounding errors when fractional values are represented as integers. (For example, all values in range [2.0, 2.3] might be represented in a single bucket.) Problematically, when the lossy numbers are used in several computations, the losses accumulate and need to be rescaled for the next computation.

You might also like

Algorithm helps artificial intelligence systems dodge ‘adversarial’ inputs

Assessing regulatory fairness through machine learning

Raspberry Pi to get machine learning boost

The QAT API solves this by simulating low-precision computation during the AI model training process. Quantization error is introduced as noise throughout the training, which QAT API’s algorithm tries to minimize so that it learns variables that are more robust to quantization. A training graph leverages operations that convert floating-point objects into low-precision values and then convert low-precision values back into floating-point, ensuring that quantization losses are introduced in the computation and that further computations emulate low-precision.

In tests, Google reports that an image classification model (MobilenetV1 224) with a non-quantized accuracy of 71.03% achieved 71.06% accuracy after quantization when tested on the open source Imagenet data set. Another classification model (Nasnet-Mobile) tested against the same data set only experienced a 1% loss in accuracy (74% to 73%) post-quantization.

Aside from emulating the reduced precision computation, QAT API is responsible for recording the statistics necessary to quantize a trained model or parts of it. This enables developers to convert a model trained with the API to a quantized integer-only TensorFlow Lite model, for example, or to experiment with various quantization strategies while simulating how quantization affects accuracy for different hardware backends.

Google says that by default, QAT API — which is a part of the TensorFlow Model Optimization Toolkit — is configured to work with the quantized execution support available in TensorFlow Lite, Google’s toolset designed to adapt models architected on its TensorFlow machine learning framework to mobile, embedded, and internet of things devices. “We are very excited to see how the QAT API further enables TensorFlow users to push the boundaries of efficient execution in their TensorFlow Lite-powered products as well as how it opens the door to researching new quantization algorithms and further developing new hardware platforms with different levels of precision,” wrote Google in a blog post.

The formal launch of the QAT API comes after the unveiling of TensorFlow Quantum, a machine learning framework for training quantum models, at the TensorFlow Dev Summit. The QAT API was previewed during a recorded session at the conference.

Credit: Google News

Previous Post

Robots and Sensory Experiences - Becoming Human: Artificial Intelligence Magazine

Next Post

Zoom's fall: Google bans Zoom from staffers' gear

Related Posts

Algorithm helps artificial intelligence systems dodge ‘adversarial’ inputs
Machine Learning

Algorithm helps artificial intelligence systems dodge ‘adversarial’ inputs

March 9, 2021
Assessing regulatory fairness through machine learning
Machine Learning

Assessing regulatory fairness through machine learning

March 8, 2021
Raspberry Pi to get machine learning boost
Machine Learning

Raspberry Pi to get machine learning boost

March 8, 2021
Dataiku named as Gartner Leader for Data Science and Machine Learning
Machine Learning

Dataiku named as Gartner Leader for Data Science and Machine Learning

March 8, 2021
Machine Learning Patentability In 2019: 5 Cases Analyzed And Lessons Learned Part 4 – Intellectual Property
Machine Learning

Podcast: Non-Binding Guidance: FDA Regulatory Developments In AI And Machine Learning – Food, Drugs, Healthcare, Life Sciences

March 8, 2021
Next Post
Zoom’s fall: Google bans Zoom from staffers’ gear

Zoom's fall: Google bans Zoom from staffers' gear

Leave a Reply Cancel reply

Your email address will not be published. Required fields are marked *

Recommended

Plasticity in Deep Learning: Dynamic Adaptations for AI Self-Driving Cars

Plasticity in Deep Learning: Dynamic Adaptations for AI Self-Driving Cars

January 6, 2019
Microsoft, Google Use Artificial Intelligence to Fight Hackers

Microsoft, Google Use Artificial Intelligence to Fight Hackers

January 6, 2019

Categories

  • Artificial Intelligence
  • Big Data
  • Blockchain
  • Crypto News
  • Data Science
  • Digital Marketing
  • Internet Privacy
  • Internet Security
  • Learn to Code
  • Machine Learning
  • Marketing Technology
  • Neural Networks
  • Technology Companies

Don't miss it

Malware Can Exploit New Flaw in Intel CPUs to Launch Side-Channel Attacks
Internet Privacy

Malware Can Exploit New Flaw in Intel CPUs to Launch Side-Channel Attacks

March 9, 2021
How to Begin Using DevSecOps for your Team
Data Science

How to Begin Using DevSecOps for your Team

March 9, 2021
Algorithm helps artificial intelligence systems dodge ‘adversarial’ inputs
Machine Learning

Algorithm helps artificial intelligence systems dodge ‘adversarial’ inputs

March 9, 2021
Why Use Python for AI and Machine Learning? | by BoTreeTechnologies | Mar, 2021
Neural Networks

Why Use Python for AI and Machine Learning? | by BoTreeTechnologies | Mar, 2021

March 9, 2021
Podcasts for marketers and Google’s stance on tracking: Monday’s daily brief
Digital Marketing

Podcasts for marketers and Google’s stance on tracking: Monday’s daily brief

March 9, 2021
13 challenges creating an open, scalable, and secure serverless platform – IBM Developer
Technology Companies

10 questions for modernizing your old Java applications – IBM Developer

March 9, 2021
NikolaNews

NikolaNews.com is an online News Portal which aims to share news about blockchain, AI, Big Data, and Data Privacy and more!

What’s New Here?

  • Malware Can Exploit New Flaw in Intel CPUs to Launch Side-Channel Attacks March 9, 2021
  • How to Begin Using DevSecOps for your Team March 9, 2021
  • Algorithm helps artificial intelligence systems dodge ‘adversarial’ inputs March 9, 2021
  • Why Use Python for AI and Machine Learning? | by BoTreeTechnologies | Mar, 2021 March 9, 2021

Subscribe to get more!

© 2019 NikolaNews.com - Global Tech Updates

No Result
View All Result
  • AI Development
    • Artificial Intelligence
    • Machine Learning
    • Neural Networks
    • Learn to Code
  • Data
    • Blockchain
    • Big Data
    • Data Science
  • IT Security
    • Internet Privacy
    • Internet Security
  • Marketing
    • Digital Marketing
    • Marketing Technology
  • Technology Companies
  • Crypto News

© 2019 NikolaNews.com - Global Tech Updates