ALEXANDER MORDVINTSEV

Alexander Mordvintsev is a researcher, artist, and the creative mind behind the renowned DeepDream project. Currently part of Google Research, his work revolves around the visualization, interpretation, and understanding of Deep Neural Networks. Driven by his fascination for emergent phenomena, Alexander combines his expertise in Machine Learning, Computer Graphics, and Vision to create remarkable visual interpretations of complex systems.

Recent Interview with the artist on our Editorial.

Twitter Official Website

 
Featured
Alexander Mordvintsev
sold out

SOLD

Flourishing, 2018

Unique NFT

Description:

Flourishing (2018) was created using DeepDream, a technique developed by Google engineer Alexander Mordvintsev. This artwork, showcased at Art Fair Zurich 2018, features a vibrant composition of colorful houses intertwined with surreal floral patterns, evoking a sense of flourishing nature.

DeepDream is a computer vision program developed by Google engineer Alexander Mordvintsev, utilizing a convolutional neural network (CNN) to enhance patterns in images through algorithmic pareidolia, producing surreal, psychedelic visuals. The program popularized the term "deep dreaming," referring to the generation of images that activate specific features in a trained deep network. Originating from Google's "Inception" neural network for the 2014 ImageNet Challenge, DeepDream's open-source code was released in July 2015. The process involves feeding an image into the neural network and iteratively adjusting it based on the network’s recognition of various features, amplifying edges, and shapes to create hallucinatory effects where familiar objects morph into complex, often bizarre patterns. DeepDream showcases the power of neural networks in image processing and offers insight into the workings of machine learning models, merging technology and art.

For more information please email us on info@katevassgalerie.com

Exhibited at Untitled Miami Art Fair, Miami, Kate Vass Galerie Booth A43, December 2024

Exhibited at Art Fair Zurich 2018

Alexander Mordvintsev
sold out

Just Before DeepDream: 5x5, 2015

Fine Art Print

Size: 60 x 60 cm

Unique

Description:

The DeepDream algorithm was developed through a series of experiments that led to the generation of psychedelic images filled with intricate details, capturing global attention in the summer of 2015. The "Just Before DeepDream" series presents a few images out of 1,000 that were generated before DeepDream's open-source code was released in July 2015. The network used was also different: these images were produced by AlexNet, created in 2012, which is often cited as one of the main catalysts of the Deep Learning revolution. These images already demonstrate the promising capabilities of deep nets for image generation. The series shows steps that Mordvintsev took to improve the fidelity of machine-generated images,

Exhibited at Untitled Miami Art Fair, Miami, Kate Vass Galerie Booth A43, December 2024

Alexander Mordvintsev

Prehistory: Ernst Haeckel inspired fractal art, 2009/11/17

Fine Art Print on paper

The work is also available as a unique NFT (minted upon request) for 5 ETH

This fractal artwork is not related to Deep Dream, but it represents my long-standing interest in creating life-like systems, which are one of Alex’s primary focuses today. Originally, it was part of a video and an interactive demo.

For more information, please contact info@katevassgalerie.com

Alexander Mordvintsev
sold out

SOLD OUT

DeepDream is looking for patterns everywhere #2, 2015/05

Unique NFT

Price: 5 ETH

DeepDream is looking for patterns everywhere, one of the first DeepDream images produced by its inventor, Alex Mordvintsev in May 2015 before its public release.

 DeepDream is a computer vision program developed by Google engineer Alexander Mordvintsev, utilizing a convolutional neural network (CNN) to enhance patterns in images through algorithmic pareidolia, producing surreal, psychedelic visuals. The program popularized the term "deep dreaming," referring to the generation of images that activate specific features in a trained deep network. Originating from Google's "Inception" neural network for the 2014 ImageNet Challenge, DeepDream's open-source code was released in July 2015. The process involves feeding an image into the neural network and iteratively adjusting it based on the network’s recognition of various features, amplifying edges, and shapes to create hallucinatory effects where familiar objects morph into complex, often bizarre patterns. DeepDream showcases the power of neural networks in image processing and offers insight into the workings of machine learning models, merging technology and art.

Provenance:

DeepDream is looking for patterns everywhere, created in May 2015, was minted as a unique NFT in June 2024 as part of the group show "Automat und Mensch 2.0," a retrospective of AI history at Kate Vass Galerie. While DeepDream was released in July 2015 as an open source for public use, “DeepDream is looking for patterns everywhere” was made before Google's public launch and only became allowed for sale since June 2024. This work was also featured in the article https://medium.com/kanon-log/alexander-mordvintsev-deepdream-c-2015-2021-5ba5ab55f6cf

Alexander Mordvintsev

Just before DeepDream: fractalization #3, 2015/04

Fine Art Print on paper

Size: 60 x 60 cm

The work is also available as a unique NFT (minted upon request) for 5 ETH

Description:

The Deep Dream algorithm was created in a series of experiments that led to the generation of psychedelic images full of intricate details that swept across the globe in the summer of 2015. Slides 4-8 show images that were created on the way to the final algorithm. Scientific progress is enabled by accumulation of ideas and building on the work of others. For example, p.4 “Just before DeepDream 1000 classes” shows a few images out of 1000 that were generated by the algorithm inspired by the paper . The network was also different: these images were produced by the AlexNet , created in 2012, which is often cited as one of the main triggering points of the Deep Learning revolution. These images lack the resolution and rich details, but already show promising capabilities of deep nets for image generation. The subsequent slides show steps that Alexander Mordivntsev took to improve the fidelity of the machine generations and finally giving the network more “creative freedom” by formulating the objective for amplification patterns already perceived by the network in a particular input image.

For more information please email us on info@katevassgalerie.com

Exhibited at Untitled Miami Art Fair, Miami, Kate Vass Galerie Booth A43, December 2024

Exhibited at Automat und Mensch 2.0, Kate Vass Galerie, May 2024

Alexander Mordvintsev

Just before DeepDream: 1000 classes #3, 2015/01

Fine Art Print on paper

Size: 60 × 60 cm

The work is also available as a unique NFT (minted upon request) for 5 ETH

Description:

The Deep Dream algorithm was created in a series of experiments that led to the generation of psychedelic images full of intricate details that swept across the globe in the summer of 2015. Slides 4-8 show images that were created on the way to the final algorithm. Scientific progress is enabled by accumulation of ideas and building on the work of others. For example, p.4 “Just before DeepDream 1000 classes” shows a few images out of 1000 that were generated by the algorithm inspired by the paper . The network was also different: these images were produced by the AlexNet , created in 2012, which is often cited as one of the main triggering points of the Deep Learning revolution. These images lack the resolution and rich details, but already show promising capabilities of deep nets for image generation. The subsequent slides show steps that Alexander Mordivntsev took to improve the fidelity of the machine generations and finally giving the network more “creative freedom” by formulating the objective for amplification patterns already perceived by the network in a particular input image.

For more information please email us on info@katevassgalerie.com

Exhibited at Untitled Miami Art Fair, Miami, Kate Vass Galerie Booth A43, December 2024

Exhibited at Automat und Mensch 2.0, Kate Vass Galerie, May 2024

Alexander Mordvintsev

Just before DeepDream: 1000 classes #2, 2015/01

Fine Art Print on paper

Size: 60 x 60 cm

The work is also available as a unique NFT (minted upon request) for 5 ETH

Description:

The Deep Dream algorithm was created in a series of experiments that led to the generation of psychedelic images full of intricate details that swept across the globe in the summer of 2015. Slides 4-8 show images that were created on the way to the final algorithm. Scientific progress is enabled by accumulation of ideas and building on the work of others. For example, p.4 “Just before DeepDream 1000 classes” shows a few images out of 1000 that were generated by the algorithm inspired by the paper . The network was also different: these images were produced by the AlexNet , created in 2012, which is often cited as one of the main triggering points of the Deep Learning revolution. These images lack the resolution and rich details, but already show promising capabilities of deep nets for image generation. The subsequent slides show steps that Alexander Mordivntsev took to improve the fidelity of the machine generations and finally giving the network more “creative freedom” by formulating the objective for amplification patterns already perceived by the network in a particular input image.

For more information please email us on info@katevassgalerie.com

Exhibited at Untitled Miami Art Fair, Miami, Kate Vass Galerie Booth A43, December 2024

Exhibited at Automat und Mensch 2.0, Kate Vass Galerie, May 2024

Alexander Mordvintsev
sold out

Sunset, 2015/05

SOLD OUT

Fine Art Print on paper

Size: around 60 x 85 cm

The work is also available as a unique NFT (minted upon request) for 5 ETH

Sunset, 2015/05 is one of the first DeepDream images produced by its inventor, Alex Mordvintsev in May 2015 before its public release.

DeepDream is a computer vision program developed by Google engineer Alexander Mordvintsev, utilizing a convolutional neural network (CNN) to enhance patterns in images through algorithmic pareidolia, producing surreal, psychedelic visuals. The program popularized the term "deep dreaming," referring to the generation of images that activate specific features in a trained deep network. Originating from Google's "Inception" neural network for the 2014 ImageNet Challenge, DeepDream's open-source code was released in July 2015. The process involves feeding an image into the neural network and iteratively adjusting it based on the network’s recognition of various features, amplifying edges, and shapes to create hallucinatory effects where familiar objects morph into complex, often bizarre patterns. DeepDream showcases the power of neural networks in image processing and offers insight into the workings of machine learning models, merging technology and art.

Created in May 2015, minted as a unique NFT on request as part of the group show "Automat und Mensch 2.0," a retrospective of AI history at Kate Vass Galerie. While DeepDream was released in July 2015 as an open source for public use, Sunset was made before Google's public launch and only became allowed for sale since June 2024.

For more information, please contact info@katevassgalerie.com

Alexander Mordvintsev
sold out

SOLD OUT

Custard Apple, 2015/05

Fine Art Print on paper

Size: 60 x 60 cm

The work is also available as a unique NFT (minted upon request) for 5 ETH

Custard Apple is one of the first DeepDream images produced by its inventor, Alex Mordvintsev in May 2015 before its public release.

DeepDream is a computer vision program developed by Google engineer Alexander Mordvintsev, utilizing a convolutional neural network (CNN) to enhance patterns in images through algorithmic pareidolia, producing surreal, psychedelic visuals. The program popularized the term "deep dreaming," referring to the generation of images that activate specific features in a trained deep network. Originating from Google's "Inception" neural network for the 2014 ImageNet Challenge, DeepDream's open-source code was released in July 2015. The process involves feeding an image into the neural network and iteratively adjusting it based on the network’s recognition of various features, amplifying edges, and shapes to create hallucinatory effects where familiar objects morph into complex, often bizarre patterns. DeepDream showcases the power of neural networks in image processing and offers insight into the workings of machine learning models, merging technology and art.

Created in May 2015, minted as a unique NFT on request as part of the group show "Automat und Mensch 2.0," a retrospective of AI history at Kate Vass Galerie. While DeepDream was released in July 2015 as an open source for public use, Custard Apple was made before Google's public launch and only became allowed for sale since June 2024. This work was also featured in a 2018 article by curator Jason Bailey.

https://www.artnome.com/news/2018/12/30/deepdream-creator-unveils-very-first-images-after-three-years

For more information, please contact info@katevassgalerie.com

Alexander Mordvintsev
sold out

SOLD OUT

Father Cat, 2015/05

Unique NFT

Price: 5 ETH

Father Cat, one of the first DeepDream images produced by its inventor, Alex Mordvintsev in May 2015 before its public release.

DeepDream is a computer vision program developed by Google engineer Alexander Mordvintsev, utilizing a convolutional neural network (CNN) to enhance patterns in images through algorithmic pareidolia, producing surreal, psychedelic visuals. The program popularized the term "deep dreaming," referring to the generation of images that activate specific features in a trained deep network. Originating from Google's "Inception" neural network for the 2014 ImageNet Challenge, DeepDream's open-source code was released in July 2015. The process involves feeding an image into the neural network and iteratively adjusting it based on the network’s recognition of various features, amplifying edges, and shapes to create hallucinatory effects where familiar objects morph into complex, often bizarre patterns. DeepDream showcases the power of neural networks in image processing and offers insight into the workings of machine learning models, merging technology and art.

 Provenance:

“Father Cat”, created in May 2015, was minted as a unique NFT in June 2024 as part of the group show "Automat und Mensch 2.0," a retrospective of AI history at Kate Vass Galerie. While DeepDream was released in July 2015 as an open source for public use, “Father Cat” was made before Google's public launch and only became allowed for sale since June 2024. This work was also featured in a 2018 article by curator Jason Bailey.

https://www.artnome.com/news/2018/12/30/deepdream-creator-unveils-very-first-images-after-three-years  

Alexander Mordvintsev
sold out

SOLD OUT

Cats, 2015/05

Unique NFT

Price: 5 ETH

Cats, one of the first DeepDream images produced by its inventor, Alex Mordvintsev in May 2015 before its public release.

DeepDream is a computer vision program developed by Google engineer Alexander Mordvintsev, utilizing a convolutional neural network (CNN) to enhance patterns in images through algorithmic pareidolia, producing surreal, psychedelic visuals. The program popularized the term "deep dreaming," referring to the generation of images that activate specific features in a trained deep network. Originating from Google's "Inception" neural network for the 2014 ImageNet Challenge, DeepDream's open-source code was released in July 2015. The process involves feeding an image into the neural network and iteratively adjusting it based on the network’s recognition of various features, amplifying edges, and shapes to create hallucinatory effects where familiar objects morph into complex, often bizarre patterns. DeepDream showcases the power of neural networks in image processing and offers insight into the workings of machine learning models, merging technology and art.

Provenance:

"Cats," created in May 2015, was minted as a unique NFT in June 2024 as part of the group show "Automat und Mensch 2.0," a retrospective on AI history at Kate Vass Galerie. The artwork was first shown in May 2019 as a small physical print, not for sale and included in multiple publications since then. Although DeepDream was released in July 2015 as an open-source for public, "Cats" was created before this public launch and was only permitted for sale since June 2024. This work was also featured in a 2018 article by curator Jason Bailey.

https://www.artnome.com/news/2018/12/30/deepdream-creator-unveils-very-first-images-after-three-years  

Alex Mordvintsev, Sparks (Video)