GLOSSARY ENTRY (DERIVED FROM QUESTION BELOW) | ||||||
---|---|---|---|---|---|---|
|
22:56 Apr 20, 2020 |
English to Spanish translations [PRO] General / Conversation / Greetings / Letters | |||||||
---|---|---|---|---|---|---|---|
|
| ||||||
| Selected response from: Beatriz Ramírez de Haro Spain Local time: 22:22 | ||||||
Grading comment
|
Summary of answers provided | ||||
---|---|---|---|---|
3 +4 | ver dentro |
| ||
3 -2 | ensenhar (la computadora) a ver imagenes con defectos |
|
Discussion entries: 4 | |
---|---|
trained as containing ensenhar (la computadora) a ver imagenes con defectos Explanation: The computer is trained to recognize images containing defects, that is anomalies, things not expected. Learning in the program takes time and many examples. Se toma fotos de los productos, incluyendo los con defectos, o variaciones. Literalmente, hay que** entrenar conteniendo defectos***. vease a ;https://towardsdatascience.com/train-image-recognition-ai-wi... En la http dice; concept of Machine Learning was introduced and it ushered in an era in which instead of telling computers what to look out for in recognizing scenes and objects in images and videos, we can instead design algorithms that will make computers to learn how to recognize scenes and objects in images by itself, just like a child learns to understand his/her environment by exploring. Machine learning opened the way for computers to learn to recognize almost any scene or object we want them too. -------------------------------------------------- Note added at 21 hrs (2020-04-21 20:14:28 GMT) -------------------------------------------------- http://xinleic.xyz/papers/iccv13.pdf ""We propose NEIL (Never Ending Image Learner), a computer program that runs 24 hours per day and 7 days per week to automatically extract visual knowledge from Internet data. NEIL uses a semi-supervised learning algorithm that jointly discovers common sense relationships (e.g., “Corolla is a kind of/looks similar to Car”,“Wheel is a part of Car”) and labels instances of the given visual categories. It is an attempt to develop the world’s largest visual structured knowledge base with minimum human labeling effort. As of 10th October 2013, NEIL has been continuously running for 2.5 months on 200 core cluster (more than 350K CPU hours) and has an ontology of 1152 object categories, 1034 scene categories and 87 attributes. During this period, NEIL has discovered more than 1700 relationships and has labeled more than 400K visual instances. -------------------------------------------------- Note added at 21 hrs (2020-04-21 20:16:54 GMT) -------------------------------------------------- Quote op cite "Las computadoras ya consiguen identificar y etiquetar los objetos utilizando la visión artificial de la máquina, pero los investigadores esperan que NEIL aprenda las relaciones entre los diferentes elementos sin ***que hayan sido previamente enseñados.*** Example sentence(s):
|
| |||||||||||||
11 hrs confidence: peer agreement (net): +4
|