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 / Rama Ramakrishnan.

Format:

Book

Author/Creator:

Ramakrishnan, Rama, author.

Language:

English

Subjects (All):

Artificial intelligence--Industrial applications.

Artificial intelligence.

Business intelligence--Data processing.

Business intelligence.

Management--Data processing.

Management.

Physical Description:

1 online resource (11 pages) : illustrations

Edition:

[First edition].

Place of Publication:

[Cambridge, Massachusetts] : MIT Sloan Management Review, 2022.

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.

Notes:

OCLC-licensed vendor bibliographic record.

"Reprint 64202."

OCLC:

1354563813

Publisher Number:

53863MIT64202