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

Category Members openFrameworksPosted 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

/++

It’s doing it – Online exhibition of computer generated images that autonomously update

Created as a collaboration between 9 artists, It’s doing it is an online group exhibition of computer generated images that autonomously updates on a daily basis over the course of 45 days. All of the works in the show are instruction-based artworks expressed through computer programs written by the artists. These programs generate new images once daily that can be viewed on the website.

Tense Relations: human vs. machine art and aesthetics at BIAN

CAN contributor Dylan Schenker considers AUTOMATA (“art made by machines for machines”) and the uneasy relation between human and machine aesthetics at the third edition of Montreal’s BIAN digital art biennale.

Audio Geometry Exploration – Sonification in Houdini

Created by Simon Russell, animation director based in London, the following is a series of Houdini experiments where geometry is used as a way to visualise sound, and vice versa.

Interactive Wall at UD [openFrameworks, Kinect]

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.