cool_system

[cool-system]

🛋

[cool-system]

[cool-system]

🔥🔥🔥 (à Pizza grill kebab)

[cool-system]

mf (à Desert Hills Video Security Systems)

[claymahn]

c,b,s (contrapposto)

[a-sym-metric]

[sometimes-now]

works by steve bishop.

[cool-system]

[prostheticknowledge]

Interactive Example Based Terrain Authoring with Conditional Adversarial Networks

Graphics research from LIRIS, Purdue University and Ubisoft is method of generating 3D landscape terrain from simple pen markings with the assistance of neural networks:

Authoring virtual terrains presents a challenge and there is a strong need for authoring tools able to create realistic terrains with simple user-inputs and with high user control. We propose an example-based authoring pipeline that uses a set of terrain synthesizers dedicated to specific tasks. Each terrain synthesizer is a Conditional Generative Adversarial Network trained by using real-world terrains and their sketched counterparts. The training sets are built automatically with a view that the terrain synthesizers learn the generation from features that are easy to sketch. During the authoring process, the artist first creates a rough sketch of the main terrain features, such as rivers, valleys and ridges, and the algorithm automatically synthesizes a terrain corresponding to the sketch using the learned features of the training samples. Moreover, an erosion synthesizer can also generate terrain evolution by erosion at a very low computational cost. Our framework allows for an easy terrain authoring and provides a high level of realism for a minimum sketch cost. We show various examples of terrain synthesis created by experienced as well as inexperienced users who are able to design a vast variety of complex terrains in a very short time. 

Link

[cool-system]

💿💿💿

[cool-system]

online 24/7

[prostheticknowledge]

flyAI

Installation by David Bowen features a colony of houseflies monitored with artificial intelligence controlling their wellbeing:

The installation uses the TensorFlow machine learning image recognition library to classify images of live houseflies. As the flies fly and land in front of a camera their image is captured. The captured image is classified by the image recognition software and what the software guesses it is looking at is ranked 1 through 5 and output. Each ranking is assigned a percentage based on how likely the software thinks that this is what it is looking at.

If “fly” is ranked number 1 on the list, a pump delivers water and nutrients to the colony based on the percentage of the ranking. If “fly” is not ranked number 1 the pump does not deliver water and nutrients to the colony. The system is setup to run indefinitely with an indeterminate outcome.

Link

[prostheticknowledge]

telekniting

Installation by vtol creates a continuously coloured thread based on an incoming television signal:

The concept of the project is to transform the television signal into a multicolored thread that wraps around any object installed on a rotating table. The installation picks up a TV signal in real-time mode and scales it down to a single-pixel image. A special program gradually lowers the digital image resolution. Each time the number of pixels is cut by half, until the image becomes a single pixel, the color of which is the one dominating in each specific frame. 

… The concept of the project is to ironically transform and reduce the trivial and annoying data stream into a creatively different kind of interpretation. A one-dimensional materialized lo-fi stream covers and mantles familiar objects. Weaving and spinning looms are the ancestors of these project. Over the millennia, they served people as idiosyncratic coding devices and programming tools that dealt with innermost archetypal stratums of culture. 

More Here

[cool-system]

I dedicate this video to all people i love

[cool-system]

[CSR004] Virtual Crusade https://soundcloud.com/coolsystem_radio

[prostheticknowledge]

Interactive Neural Network Art

Webapp by hardmaru lets you create abstract images based on neural network setup, coded in javascript:

After a recent blog post where I demonstrated a really simple method to generate high resolution abstract images with neural networks and latent vectors, many people were wondering if they can use this method without the need to setup TensorFlow.  Although there were some code available previously in Javascript, it wasn’t general enough to use as a tool for a digital artist.

So I took the Javascript code previously written and spent an hour or two to fine tuned it into a simple web app.  Karpathy’s recurrent.js library makes it really easy to implement highly customised neural networks in JS, and adopts a computational graph type of method similar to modern libraries.  Using these tools, and JQuery, I incorporated latent vectors into the previous JS model, as well as options for different colour models, and alpha-transparency modes.  In addition, the user is able to specify the size and depth of the generator neural network.

You can find out more coding background here

If you want to create your own abstract images, you can check out the webapp here

[cool-system]

Persis K - Crash 177

[CSR003] Radiations - EP 2016 free track https://soundcloud.com/coolsystem_radio

[vhspositive]