Latent Lab: Exploration Beyond Search and Synthesis

This Master’s thesis investigates the potential of artificial intelligence (AI) models, particularly machine learning and natural language processing techniques, to facilitate brainstorming and ideation in the invention process. The thesis centers around the iterative development of “Latent Lab,” an interactive tool for exploring relationships among MIT Media Lab research projects. The work offers insights into AI systems as co-inventors by addressing the challenges of organizing, searching, and synthesizing content. Our method for interacting with the material is based on “exploration” rather than search. The primary objective was to create a human-AI co-invention system and evaluate its performance on the novelty of co-created ideas. However, the research underscored the importance of accurate data organization for meaningful data generation. Consequently, later versions of Latent Lab focused primarily on improving data organization and interactive exploration. The tool’s success was measured by its effectiveness in familiarizing users with research projects at the Media Lab, ultimately laying the foundation for the future development of human-AI co-invention systems.

Name thesis:degree_name

Master

Department dc:contributor.department

Program in Media Arts and Sciences (Massachusetts Institute of Technology)

Grantor dc:publisher

Massachusetts Institute of Technology

Year dc:date.issued

2023

Author dc:creator

• Dunnell, Kevin F.

Advisor dc:contributor.advisor

• Lippman, Andrew B.

Statement dc:rights

• In Copyright - Educational Use Permitted
• Copyright retained by author(s)

Licence dc:rights.uri

• https://rightsstatements.org/page/InC-EDU/1.0/

Handle dc:identifier.uri

https://hdl.handle.net/1721.1/151986

OAI identifier oai:identifier

oai:dspace.mit.edu:1721.1/151986