Cover Image
Read Now

How to build good AI solutions when data is scarce data-efficient AI techniques are emerging, and that means you don't always need large volumes of labeled data to train AI systems based on neural networks

Developing AI systems based on neural networks can require large volumes of labeled training data, which can be hard to obtain in some settings. New techniques for reducing the number of labeled examples needed to build accurate models are now emerging to address this problem. These approaches encom...

Full description

Bibliographic Details
Main Author: Ramakrishnan, Rama
Format: eBook
Language:English
Published: [Cambridge, Massachusetts] MIT Sloan Management Review 2022
Edition:[First edition]
Subjects:
Gestion / Informatique
Management / Data Processing / Fast
Management / Data Processing / Http://id.loc.gov/authorities/subjects/sh85080339
Artificial Intelligence / Industrial Applications
Artificial Intelligence / Industrial Applications / Fast
Business Intelligence / Data Processing
Intelligence Artificielle / Applications Industrielles
Online Access:
Collection: O'Reilly - Collection details see MPG.ReNa
Description
Summary:Developing AI systems based on neural networks can require large volumes of labeled training data, which can be hard to obtain in some settings. New techniques for reducing the number of labeled examples needed to build accurate models are now emerging to address this problem. These approaches encompass ways to transfer models across related problems and to pretrain models with unlabeled data. They also include emerging best practices around data-centric artificial intelligence
Item Description:"Reprint 64202."
Physical Description:11 pages illustrations

Similar Items