Phase Transitions in Artificial Intelligence Systems
By Bernardo A. Huberman, Tad Hogg. 1987
Subfields: Statistical Learning Theory, AI for Physical Sciences
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Statistical Learning Theory
In AI for Physical Sciences
Citations in the corpus
- Emergent Abilities of Large Language Models (2022, neutral): “This qualitative change is also known as a phase transition—a dramatic change in overall behavior that would not have been foreseen by examining smaller-scale systems (Huberman and Hogg, 1987).”
- A Survey of Large Language Models (2023, unknown): “pattern has close connections with the phenomenon of phase transition in physics [31, 58].”
- Implications of Recursive Distributed Representations (1988, background): “For example both (Hubennan & Hogg, 1987) and (Kurten, 1987) show how phase-transitions occur in particular neural-like systems, and (Lapedes & Farber, 1988b) demonstrate how a network trained to predict a simple iterated function would follow that function's bifurcations into chaos.”
- The Induction of Dynamical Recognizers (1991, background): “But chaotic behavior has shown up repeatedly in studies of neural networks (Derrida & Meir, 1988; Huberman & Hogg, 1987; Kolen & Pollack, 1990; Kurten, 1987; van der Maas et al., 1990), and a few scientists have begun to explore how this dynamical complexity could be exploited for useful purposes,…”
- SAT-based analysis of feature models is easy (2009, background): “The difficult problems lie in the middle of the spectrum, in the so called transition phase [26].”