When:
Monday, May 5, 2025
4:30 PM - 6:00 PM CT
Where: University Hall, Hagstrum 201, 1897 Sheridan Road, Evanston, IL 60208 map it
Audience: Faculty/Staff - Public - Post Docs/Docs - Graduate Students
Cost: FREE
Contact:
Janet Hundrieser
(847) 491-3525
Group: Science in Human Culture Program - Klopsteg Lecture Series
Category: Lectures & Meetings
Speaker
James E. Dobson - English, Dartmouth University
Title
"Neural Network Computing Before GPU's"
Abstract
High-speed, high-memory, multicore graphics processing units such as those sold by Nvidia Corporation are the dominant enabling technology for contemporary deep learning. These specialized computing devices offload mathematically complex operations from general purpose CPUs. While these devices seemingly appear as novel technologies designed for the generative AI age, they have been around for decades as part of the development of computer graphics and visual computing, a history recounted in Jacob Gaboury’s recent Image Objects: An Archaeology of Computer Graphics. This talk places today’s latest GPUs in a parallel genealogy, that of the more than seventy-year-old search for alternatives to general purpose digital computers based on neural network architectures. That project runs through the development of early learning machines including Frank Rosenblatt’s Perceptron and Tobermory to Hopfield network-inspired systems in the 1980s and 1990s such as the massively parallel high-performance computers produced by nCUBE, MasPar, and Thinking Machines. Despite these developments and the success of contemporary technologies, the tendency in computing has been toward simulation and general-purpose computers. In tracking the material history of specialized processors alongside today’s popular artificial neural network architectures, we may better understand their interrelation and the prospects for the continued relevance of these devices.
Biography
I am a literary and cultural critic who specializes in intellectual history and U.S. autobiographical writing in the nineteenth and twentieth centuries. I use a number of approaches--theoretical, historical, formalist, and computational (sometimes called "digital humanities" or "cultural analytics")--to answer persistent intellectual problems. I am thus also interested in the critical analysis of twentieth-century and contemporary computation methods including machine learning, computer vision, and various approaches to text and data mining.