/neural networks (6)
The chAIr Project is a series of four chairs created using a generative neural network (GAN) trained on a dataset of iconic 20th-century chairs with the goal to “generate a classic”. The results are semi-abstract visual prompts for a human designer who used them as a starting point for actual chair design concepts.
09/08/2018Latest 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.
20/03/2018Neural Network experiment by Eddie Lee uses evolutionary NN to simulate AI path finding of Froggy-style game mechanic. Every generation, it chooses the “fittest” critters and asexually reproduces them.
18/07/2017Created by Refik Anadol in collaboration with Google’s Artists and Machine Intelligence program, ‘Archive Dreaming’ is a 6 meters wide circular installation that employs machine learning algorithms to search and sort relations among 1,700,000 documents.
25/05/2017Latest in the series of critical design projects by Shanghai design and research studio Automato, TraiNNing Cards is a set of 5000 training images, physically printed and handpicked by humans to train any of your machines to recognise first and favorite item in a house: a dog.
01/02/2017Created by a Golan Levin, David Newbury, and Kyle McDonald, with the assistance of Golan’s students at CMU, Terrapattern is a visual search tool for satellite imagery that provides journalists, citizen scientists, and other researchers with the ability to quickly scan large geographical regions for specific visual features.
25/05/2016The chAIr Project is a series of four chairs created using a generative neural network (GAN) trained on a dataset of iconic 20th-century chairs with the goal to “generate a classic”. The results are semi-abstract visual prompts for a human designer who used them as a starting point for actual chair design concepts.
Tags: ai / automation / collaboration / design / featured / furniture / furniture design / machine learning / neural networks / Philipp Schmitt / Steffen Weiss
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.
Tags: camera / computer vision / experiment / featured / knowledge / learning / machine learning / memo akten / neural networks / openFrameworks / process / reality
Neural Network experiment by Eddie Lee uses evolutionary NN to simulate AI path finding of Froggy-style game mechanic. Every generation, it chooses the “fittest” critters and asexually reproduces them.
Created by Refik Anadol in collaboration with Google’s Artists and Machine Intelligence program, ‘Archive Dreaming’ is a 6 meters wide circular installation that employs machine learning algorithms to search and sort relations among 1,700,000 documents.
Tags: archive / DirectX 11 / featured / GAN / google / installation / library / machine learning / neural networks / process / Refik Anadol / training / tSNE algorithm / vvvv
Latest in the series of critical design projects by Shanghai design and research studio Automato, TraiNNing Cards is a set of 5000 training images, physically printed and handpicked by humans to train any of your machines to recognise first and favorite item in a house: a dog.
Tags: automato / cards / creative technology / creativeappsnet / critical design / design / machine learning / media technology / neural networks / object / research / training
Created by a Golan Levin, David Newbury, and Kyle McDonald, with the assistance of Golan’s students at CMU, Terrapattern is a visual search tool for satellite imagery that provides journalists, citizen scientists, and other researchers with the ability to quickly scan large geographical regions for specific visual features.
Tags: Aman Tiwari / CMU / code / David Newbury / Golan Levin / Irene Alvarado / Kyle McDonald / machine learning / Manzil Zaheer / mapping / neural networks / p5js / Processing