|
New York City, Earth
2022
Description
How does AI understand paradox? “Twilight Crystalline Models Hunt Wistfully,” uses paradoxical phrases and impossible objects to push new neural network models to their limits. The title is a play on linguist Noam Chomsky’s intentionally strange construction “colorless green ideas sleep furiously,” a sentence that refuses clear meaning or analysis. Yet with the rise of artificial intelligence models, natural language processing and especially deep learning, even contradictory or impossible-seeming phrases can achieve a visual reality. The project combines several different neural models in a bespoke software framework, visualized as a multi-channel video, to search for impossible objects and to probe the boundary between human and machine creativity.
01
Teaming

Concept Design
Andrew Witt

Concept Design Development
Elisa Ngan

Image Generation
Bryan Ortega Welch

Model Training
George Guida

Model Visualization
Elisa Ngan

Video Compilation
Scott March Smith

Installation
Martin Fernandez

Design Coordination
Elisa Ngan
v
Teaming
Board Controls
02
Technology Research

Researching and diagramming the network for visual analysis. Identifying the number and dimensions of hidden layers to prepare for normalization.
GAN Visual Analysis
Researching and diagramming parts of the network. Identifying the number and dimensions of hidden layers to prepare for normalization.
Technology Research
GAN Decomposition
Simplifying the network into patterns of beginning (input to hidden), middle (hidden to hidden), and end (hidden to output) to identify functions. Abstracting further into parts.
Matrix Transformation Visual Analysis
Visualizing the matrix transformations for each pattern.
Technology Research
03
Concept Development

The visualization rotated through over forty select key images generated by DALL-E. The latent space between select key images was generated by training a StyleGAN model on all the key images generated through DALL-E. The latent space images were processed with a variety of Python libraries to develop an activation map of the StyleGAN model weights, using each image as a vector.
Models Orchestration
Orchestration of images that needed to be generated and processed.
Concept Development
Concept Development
04
Model Visualization

These images / vectors were manually chosen for range / diversity, and manually sorted in terms of similarity.Features are tracked through the latent space of a vector to visualize what the neuron finds meaningful at each hidden layer given all the images it has been trained on. In other words, machined neurons attempt to find meaning in machine vapors.
Samples of Activated Features
These images / vectors were manually chosen for range / diversity, and manually sorted in terms of similarity.

Features are tracked through the latent space of a vector to visualize what the neuron finds meaningful at each hidden layer given all the images it has been trained on.

In other words, machined neurons attempt to find meaning in machine vapors.
L1
L2
L3
L4
L5
L6
L7
Vector
Model Visualization
L1
L2
L3
L4
L5
L6
L7
Vector
L1
L2
L3
L4
L5
L6
L7
Vector
L1
L2
L3
L4
L5
L6
L7
Vector
Model Visualization
Model Visualization