Project 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.

Role

After receiving the trained model, I harvested the machine neuron, processing and visualizing activated features for the generated images.

Client

Certain Measures

Exhibition

Model Behavior
Cooper Union, New York
October 2022

Installation
At Cooper Union, New York City
Full Reel

v
GAN Decomposition
Researching and diagramming parts of the network. Identifying the number and dimensions of hidden layers to prepare for normalization.
GAN Patterns
Simplifying the network into patterns of beginning (input to hidden), middle (hidden to hidden), and end (hidden to output) to identify functions.
GAN Parts
Defining common part across patterns.
Matrix Transformation Diagrams
Visualizing the matrix transformations.
Model Ecosystem
My team generated the images and trained the model. I harvested the trained neurons to develop activation maps for visualization of machine vision.
Samples of Latent Space Interpolation
Key images and interpolation generated by George Guida and Bryan Ortega-Welch.
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
L1
L2
L3
L4
L5
L6
L7
Vector
L1
L2
L3
L4
L5
L6
L7
Vector
L1
L2
L3
L4
L5
L6
L7
Vector
L1
L2
L3
L4
L5
L6
L7
Vector