View allAll Photos Tagged convolutionalneuralnetwork

Minolta X700 Minolta 50mm 1:3.5 MC Macro Celtic Delta 400@800 EcoPro 1:1 04/05/2023

This Convolutional Neural Network (CNN) learned through many training samples to recognize certain objects. The network consists of several consecutive layers that have learned during the training phase to recognize different characteristics in an image and pass on this information in turn to the next layer. While the first layers recognize more primitive characteristics such as straight lines, colors, and curves, the next layers specialize in more complex forms. The network VGG16 used here is one of the best-known models of this kind.

 

Credit: Ars Electronica - Robert Bauernhansl

This Convolutional Neural Network (CNN) learned through many training samples to recognize certain objects. The network consists of several consecutive layers that have learned during the training phase to recognize different characteristics in an image and pass on this information in turn to the next layer. While the first layers recognize more primitive characteristics such as straight lines, colors, and curves, the next layers specialize in more complex forms. The network VGG16 used here is one of the best-known models of this kind.

 

This Convolutional Neural Network can be seen in the Ars Electronica Center's exhibition "Understanding AI"

 

Find out more about Understanding AI:

ars.electronica.art/center/en/exhibitions/ai/

 

Credit: Ars Electronica - Robert Bauernhansl

This Convolutional Neural Network (CNN) learned through many training samples to recognize certain objects. The network consists of several consecutive layers that have learned during the training phase to recognize different characteristics in an image and pass on this information in turn to the next layer. While the first layers recognize more primitive characteristics such as straight lines, colors, and curves, the next layers specialize in more complex forms. The network VGG16 used here is one of the best-known models of this kind.

 

Photo: Ars Electronica - Robert Bauernhansl

This Convolutional Neural Network (CNN) learned through many training samples to recognize certain objects. The network consists of several consecutive layers that have learned during the training phase to recognize different characteristics in an image and pass on this information in turn to the next layer. While the first layers recognize more primitive characteristics such as straight lines, colors, and curves, the next layers specialize in more complex forms. The network VGG16 used here is one of the best-known models of this kind.

 

Photo: Ars Electronica - Robert Bauernhansl

This is a painting I have reimagined with Google's DeepDream convolutional neural network software -- Neuroscience and Artificial Intelligence are two of my greatest passions and they are of great interest to the field of art.

 

www.keelyvanorder.com

Kyriaki Goni

Counting Craters on the Moon

 

Aksioma Project Space

Komenskega 18, Ljubljana

 

2–25 October 2019

 

Production: Aksioma - Institute for Contemporary Art, Ljubljana, 2019

 

Photo: Janez Janša

 

MORE: aksioma.org/counting.craters/

exhibition opening, 16th January 2020

 

on view until 31st January 2020

 

Filodrammatica Gallery

Rijeka, Korzo 28

 

Photo: Tanja Kanazir / Drugo more

 

More: drugo-more.hr/en/kyriaki-goni/

This Convolutional Neural Network (CNN) learned through many training samples to recognize certain objects. The network consists of several consecutive layers that have learned during the training phase to recognize different characteristics in an image and pass on this information in turn to the next layer. While the first layers recognize more primitive characteristics such as straight lines, colors, and curves, the next layers specialize in more complex forms. The network VGG16 used here is one of the best-known models of this kind.

 

Photo: Philipp Greindl

1 3 4