Profile cover photo
Profile photo
Brandon Odegard
376 followers
376 followers
About
Brandon's interests
View all
Brandon's posts

Post has attachment

Post has attachment

Post has shared content
This article claims that 150 million web pages and 1 billion customer interactions, amounting to 5TB of data, are processed every night by this company you've never heard of (unless you have), BloomReach. Apparently online retailers under pressure from Amazon and it's effective big data recommendation systems are willing to feed their data into BloomReach to get their own recommendation systems. The system customizes landing pages, search results, recommendations sections on a site, and promotions.

Post has attachment

Post has shared content
Is that husky a puppy?

A computer’s ability to accurately classify objects in images is a fundamental research focus in computer vision. Current methods of classification typically adopt a multiclass method, in which a detected object in an image is assigned a label from amongst a set of mutually exclusive labels. However, this does not capture the complexity of objects in the real world; For example, “husky”, “dog”, and “puppy” are not mutually exclusive, but while “husky” is automatically a “dog”, it may or may not be a “puppy”.

In Large-Scale Object Classification using Label Relation Graphs, University of Michigan Assistant Professor +Jia Deng along with Google co-authors Nan Ding, +Yangqing Jia, Andrea Frome, +Kevin Murphy, +Samy Bengio, Yuan Li, +Hartmut Neven, and +Hartwig Adam  introduce Hierarchy and Exclusion (HEX) graphs, a new formalism allowing flexible specification of relations between labels applied to objects in images.

Using prior knowledge about semantic label relations, the HEX graph formalism allows a “flexible specification of relations between labels applied to the same object: (1) mutual exclusion (e.g. an object cannot be dog and cat), (2) overlapping (e.g. a husky may or may not be a puppy and vice versa), and (3) subsumption (e.g. all huskies are dogs)”, providing a unified classification framework that generalizes existing models.

This work will be presented at the 2014 European Conference in Computer Vision (ECCV ‘14, http://goo.gl/DSOfeC), hosted in Zurich, Switzerland, September 6-12. To learn more, read the full paper at http://goo.gl/1O6RqT.
PhotoPhotoPhoto
2014-08-22
3 Photos - View album

Post has attachment

Post has attachment

Post has attachment

Post has shared content
Sibyl: A System for Large Scale Machine Learning at Google

Last week, at the IEEE/IFIP International Conference on Dependable Systems and Networks (DSN, http://goo.gl/KUSH7M), Google Software Engineer +Tushar Chandra gave a keynote address outlining the systems aspects of Sibyl, a supervised machine learning system that is used for solving a variety of prediction challenges, such as YouTube video recommendations.

To learn how Sibyl is being used at Google to solve internet-scale problems while using reasonable resources, watch the video below.

Post has attachment
#glassexplorers I'm trying to get him to say "Ok, Glass" as his first words. #googleglass
Photo
Wait while more posts are being loaded