Member 914
204 entries
281996 views

 RSS
(M)
YU
Immortal since Dec 17, 2007
Uplinks: 0, Generation 2

Modern video feedback art
Mimetic Mind Theater
Profile X
Teacher of physics and programmer.
  • Affiliated
  •  /  
  • Invited
  •  /  
  • Descended
  • gamma’s favorites
    From
    holographic sheets
    From michaelerule
    Simulated linear optical...
    Recently commented on
    From Wildcat
    Falling in love with AVA...
    From gamma
    Visual feedback in the...
    From syncopath
    inTensity of eXistence
    From syncopath
    Simplicity
    From Wildcat
    Some nothings are like...
    gamma’s projects
    Polytopia
    The human species is rapidly and indisputably moving towards the technological singularity. The cadence of the flow of information and innovation in...

    The Total Library
    Text that redefines...

    The great enhancement debate
    What will happen when for the first time in ages different human species will inhabit the earth at the same time? The day may be upon us when people...
    Now playing SpaceCollective
    Where forward thinking terrestrials share ideas and information about the state of the species, their planet and the universe, living the lives of science fiction. Introduction
    Featuring Powers of Ten by Charles and Ray Eames, based on an idea by Kees Boeke.
    From gamma's personal cargo

    Entertaining look at the deep learning and its details



    "... Convolutional Neural Networks are great: they recognize things, places and people in your personal photos, signs, people and lights in self-driving cars, crops, forests and traffic in aerial imagery, various anomalies in medical images and all kinds of other useful things. But once in a while these powerful visual recognition models can also be warped for distraction, fun and amusement. In this fun experiment we're going to do just that: We'll take a powerful, 140-million-parameter state-of-the-art Convolutional Neural Network, feed it 2 million selfies from the internet, and train it to classify good selfies from bad ones. Just because it's easy and because we can. And in the process we might learn how to take better selfies :)

    https://karpathy.github.io/2015/10/25/selfie/

    Sat, Jan 2, 2016  Permanent link

      RSS for this post
    Add comment
      Promote
      
      Add to favorites
    Create synapse
     
     
          Cancel