How computers are learning to be creative

bluesky on 29/06/2016 - 20:12

This TED talk (about 17 mins) is absolutely fascinating!

How computers are learning to be creative

We're on the edge of a new frontier in art and creativity — and it's not human. Blaise Agüera y Arcas, principal scientist at Google, works with deep neural networks for machine perception and distributed learning. In this captivating demo, he shows how neural nets trained to recognize images can be run in reverse, to generate them. The results: spectacular, hallucinatory collages (and poems!) that defy categorization. "Perception and creativity are very intimately connected," Agüera y Arcas says. "Any creature, any being that is able to do perceptual acts is also able to create."

Computing

Comments

  • the-mal on 29/06/2016 - 20:58
    +1

    Any time I dabble with neural networks and deep learning I am blown away by how impressive some of the implementations are. The speed of artificial intelligence and machine learning development at the moment is beyond belief. And no sign of slowing down.

    It's 50% thrillingly exciting, 50% terrifying.

  • kywst on 29/06/2016 - 21:19
    +1

    I've dabbled with feed forward NN up to boolean logic determination … don't have the time to delve into it much deeper. The problem is the vast amounts of data required to train your NN as soon as it goes beyond boolean is insane. Very excited @ Google's AlphaGo as the training data was given to the algorithm without context or expectations. This is new and exciting.

    • bluesky on 29/06/2016 - 21:51

      AI in general, has gotten more exciting, now that artificial general intelligence may just be within grasp.

      Quoting AlphaGo - Wiki

      When compared with Deep Blue or with Watson, AlphaGo's underlying algorithms are potentially more general-purpose, and may be evidence that the scientific community is making progress toward artificial general intelligence.

      Dabbled with AI a while back, when approaches (e.g. cognitive modeling) were very task-oriented in narrowly-focused domains. Progress is gathering pace, and that is exciting to see.

  • altomic on 29/06/2016 - 22:55

    aI has gone further than they let us know

    • kywst on 29/06/2016 - 23:03

      We're yet to make it to the moon and aluminium foil can also be … a hat.

      Been watching Person of Interest ay?

Login or Join to leave a comment
Login Join