Learning To See – Making deep neural network predictions on live camera input

Category Members openFrameworks People Posted on:

Latest in the series of experiments and explorations into neural networks by Memo Akten is a pre-trained deep neural network able to make predictions on live camera input – trying to make sense of what it sees, in context of what it’s seen before.

Learning To See is an ongoing series of works that use state-of-the-art Machine Learning algorithms as a means of reflecting on ourselves and how we make sense of the world. The picture we see in our conscious minds is not a direct representation of the outside world, or of what our senses deliver, but is of a simulated world, reconstructed based on our expectations and prior beliefs. Artificial neural networks loosely inspired by our own visual cortex look through surveillance cameras and try to make sense of what they are seeing. Of course they can see only what they already know. Just like us.

Sorry, this is Members Only content. Please Log-in.

Join us today by becoming a Member.

  • Archive: More than 3,500 project profiles, scores of essays, interviews and reviews.
  • Publish: Post your projects, events, announcements.
  • No Ads: No advertisements, miners, banners.
  • Education: Tutorials (beginners and advanced) with code examples, downloads.
  • Jobs Archive: Find employers who have recruited here in the past (over 800 jobs).
  • Discounts: Special offers and giveaways (events, books and media).

Become a Member

/++

object blue & TSVI: Thought Experiment – Organic to electronic evolutionary processes

Created by Matteo Zamagni, this video speculates the shift from organic to electronic evolutionary processes. Cybernetic organisms, partly made of organic structures and part electronic components respond to their environment in a variety of ways at an ever-increasing speed.

Positions of the Unknown – Tracking 52 secret satellites in Earth’s orbit

Created by Juliane Götz and Sebastian Neitsch of Quadrature and currently on view within the Ars Electronica exhibition at the DRIVE Volkswagen Group Forum in Berlin, “Positions of the Unknown” is an installation of 52 custom-made mini machines that, ever so slowly, track unidentified objects (possibly classified satellites) in Earth’s orbit.

He Liked Thick Word Soup – Software experiment about text, space and time

He Liked Thick Word Soup is the latest experiment in the Chronotext series, a growing collection of software experiments exploring the relation between text, space and time.

Data-Driven Material Modeling at the MIT Media Lab’s Mediated Matter Group

Developed at the MIT Media Lab’s Mediated Matter Group, ‘Data-Driven Material Modeling’ refers specifically to the process of the creation of high-resolution, geometrically complex, and materially heterogeneous 3D printed objects at product scale.

/+

/++

McLaren P12 Teaser ‘McLaren vs Aerodynamics’ by MLF

Sorry, this is Members Only content. Please Log-in. Join us today by becoming a Member. Archive: More than 3,500 project profiles, scores of essays, interviews and reviews.Publish: Post your projects, events, announcements.No Ads: No advertisements, miners, banners.Education: Tutorials (beginners and advanced) with code examples, downloads.Jobs Archive: Find employers who have recruited here in the past…

Leave a Reply

Your email address will not be published. Required fields are marked *