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...

Descripción completa

Detalles Bibliográficos
Clasificación:Libro Electrónico
Autor principal: Ramakrishnan, Rama (Autor)
Formato: Electrónico eBook
Idioma:Inglés
Publicado: [Cambridge, Massachusetts] : MIT Sloan Management Review, 2022.
Edición:[First edition].
Temas:
Artificial intelligence > Industrial applications.
Business intelligence > Data processing.
Management > Data processing.
Acceso en línea:Texto completo (Requiere registro previo con correo institucional)

MARC

LEADER 00000cam a22000007i 4500
001 OR_on1354563813
003 OCoLC
005 20231017213018.0
006 m o d
007 cr cnu|||unuuu
008 221213s2022 maua ob 000 0 eng d
040 |a ORMDA  |b eng  |e rda  |e pn  |c ORMDA  |d OCLCF 
024 8 |a 53863MIT64202 
029 1 |a AU@  |b 000073244358 
035 |a (OCoLC)1354563813 
037 |a 53863MIT64202  |b O'Reilly Media 
050 4 |a TA347.A78 
082 0 4 |a 006.3  |2 23/eng/20221213 
049 |a UAMI 
100 1 |a Ramakrishnan, Rama,  |e author. 
245 1 0 |a How to build good AI solutions when data is scarce :  |b 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 /  |c Rama Ramakrishnan. 
250 |a [First edition]. 
264 1 |a [Cambridge, Massachusetts] :  |b MIT Sloan Management Review,  |c 2022. 
300 |a 1 online resource (11 pages) :  |b illustrations 
336 |a text  |b txt  |2 rdacontent 
337 |a computer  |b c  |2 rdamedia 
338 |a online resource  |b cr  |2 rdacarrier 
500 |a "Reprint 64202." 
504 |a Includes bibliographical references. 
520 |a 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. 
590 |a O'Reilly  |b O'Reilly Online Learning: Academic/Public Library Edition 
650 0 |a Artificial intelligence  |x Industrial applications. 
650 0 |a Business intelligence  |x Data processing. 
650 0 |a Management  |x Data processing. 
650 7 |a Artificial intelligence  |x Industrial applications.  |2 fast  |0 (OCoLC)fst00817262 
650 7 |a Management  |x Data processing.  |2 fast  |0 (OCoLC)fst01007162 
856 4 0 |u https://learning.oreilly.com/library/view/~/53863MIT64202/?ar  |z Texto completo (Requiere registro previo con correo institucional) 
994 |a 92  |b IZTAP 

Ejemplares similares