Profile

Cover photo
Jordi Montes Sanabria
Attends Universitat Politècnica de Catalunya
Lives in Alella
57 followers|5,824 views
AboutPostsPhotosVideos

Stream

Jordi Montes Sanabria

commented on a video on YouTube.
Shared publicly  - 
 
Great!
1
Add a comment...

Jordi Montes Sanabria

commented on a video on YouTube.
Shared publicly  - 
 
Alguien puede traducirlo? Gracias
 ·  Translate
1
Add a comment...

Jordi Montes Sanabria

Shared publicly  - 
 
 
I Crawl, I See, I Learn: Teaching Computers to Think

Human beings are remarkably good at learning. Every day, our brain processes visual data from the world around us, learning common sense relationships and developing inferences about new things we may have never seen before.  For example, when faced with an image of a strange creature, we infer that it is an insect despite never having seen it before, based on its physical characteristics and the context in which the image is taken. 

But is it possible for a computer learn common sense from visual data in a fashion similar to humans, just by browsing images found on the internet? Researchers at the Robotics Institute (http://goo.gl/se0wTo) and Language Technology Institute (http://goo.gl/9aPxwH) of Carnegie Mellon University (CMU) believe so. 

Assistant Research Professor Abhinav Gupta (http://goo.gl/fG0Rbm) aims to build the world’s largest visual knowledge base with the Never Ending Image Learner (NEIL) program. Gupta, working alongside PhD student and former Google intern Abhinav Shrivastava (http://goo.gl/og37Ho) and PhD student Xinlei Chen (http://goo.gl/tQ8sCv), has developed NEIL to automatically extract visual knowledge from the Internet, enabling it to learn common sense relationships between objects and categories. For example:

Deer can be a kind of / look similar to Antelope
Car can have a part Wheels
Sunflower is/has Yellow  

Recipient of a Google Focused Research Award (http://goo.gl/hn59r) and #9 in CNN’s top 10 ideas of 2013 (http://goo.gl/cFXK1F), NEIL runs 24 hours a day, 7 days a week, using small amounts of human labeled visual data in conjunction with a large amount of unlabeled data to iteratively learn reliable and robust visual models. NEIL is then able to develop associations between different concepts, using these learned relationships to further improve the visual models themselves. This is in contrast to machine learning approaches where concepts are isolated and recognized independently. 

To date, NEIL has learned to identify 1,500 objects, 1,200 scenes, and made 2,500 associations between scene and object, from the millions of images found on the Internet. It is the hope of Gupta et al. that NEIL will learn new relationships between different concepts without the need for human labeled data, and in the process develop common sense that is needed for better for perception, reasoning and decision making.

To learn more details about NEIL and see what it has learned, visit the program page linked below.
10 comments on original post
1
Add a comment...

Jordi Montes Sanabria

Shared publicly  - 
 
Algorithms, Part I is a free online class taught by Kevin Wayne and Robert Sedgewick of Princeton University
1
Add a comment...
In his circles
72 people
Have him in circles
57 people
Helena Gan's profile photo
Alejandro Guillén's profile photo
Jose Carlos Cobo García's profile photo
Eka The Blast's profile photo
Cristian Vitales's profile photo
adria grive agusti's profile photo
Natàlia Trujillo-Bencomo's profile photo
Guillem Casanova Yñiguez's profile photo
Jessica Serrano's profile photo

Jordi Montes Sanabria

commented on a video on YouTube.
Shared publicly  - 
 
El resentido parece el... que como un empresario gana 100 veces mas que alguien ya puede ir dando lecciones de lo que esta bien y lo que esta mal.... vaya basura de video. xD
 ·  Translate
1
Add a comment...

Jordi Montes Sanabria

commented on a video on YouTube.
Shared publicly  - 
 
Que tiemble coursera.org jajaja
 ·  Translate
1
Add a comment...

Jordi Montes Sanabria

Shared publicly  - 
 
El nexus 5 te hablo desde él. Calidad precio muy muy recomendado
 ·  Translate
 
Por el momento tengo un note 2 y planeó cambiar y estoy entre el xperia Z1 el nexus 5 y el lg G2 cual me recomiendan?
 ·  Translate
64 comments on original post
1
Add a comment...
 
Buenos dias!!
Soy nuevo en la comunidad, estiy en tercero de carrera de ingenueria informatica en la UPC en barcelona.

Me gustaria saber si hay algun programadir de objectiveC por aqui de bcn o cercanias para conocernos. Un saludo!
 ·  Translate
2
1
Morururoia Lopoz Salas's profile photo
Add a comment...
People
In his circles
72 people
Have him in circles
57 people
Helena Gan's profile photo
Alejandro Guillén's profile photo
Jose Carlos Cobo García's profile photo
Eka The Blast's profile photo
Cristian Vitales's profile photo
adria grive agusti's profile photo
Natàlia Trujillo-Bencomo's profile photo
Guillem Casanova Yñiguez's profile photo
Jessica Serrano's profile photo
Work
Occupation
Ingeníero Informàtico
Places
Map of the places this user has livedMap of the places this user has livedMap of the places this user has lived
Currently
Alella
Previously
Vallirana - L'Hospitalet de llobregat
Links
Other profiles
Story
Tagline
Con frecuencia tendría que pensar lo que digo, para no decir lo que pienso.
Education
  • Universitat Politècnica de Catalunya
    Informàtica, 2010 - present
Basic Information
Gender
Male
Apps with Google+ Sign-in