Category: AI
-
Fast, slow, & metacognitive
“Fast, slow, and metacognitive thinking in AI” Inspired by the ”thinking fast and slow” cognitive theory of human decision making, we propose a multi-agent cognitive architecture (SOFAI) that is based on ”fast”/”slow” solvers and a metacognitive module. We then present experimental results on the behavior of an instance of this architecture for AI systems that…
-
The Idealized Mind
The Idealized Mind: From Model-Based Science to Cognitive Science.The open access edition of this book was made possible by generous funding and support from MIT Press Direct to Open A defense of scientific realism based on the role of idealization in the cognitive sciences. We study nature, including the mind and brain, by building scientific models.…
-
Complexity data science
“Complexity data science: A spin-off from digital twins “ Digital twins offer a new and exciting framework that has recently attracted significant interest in fields such as oncology, immunology, and cardiology. The basic idea of a digital twin is to combine simulation and learning to create a virtual model of a physical object. In this paper,…
-
AI only sees the data trail, not the human story
Cassie Kozyrkov just shared a great story: “AI only sees the data trail, not the human story“ AI only sees the past, not the future.AI only sees the pattern, not the purpose.AI only sees the data trail, not the human story.AI only sees compliance, not commitment.AI only sees keyword matches, not understanding.AI only sees what…
-
Defining intelligence: Bridging the gap
“Defining intelligence: Bridging the gap between human and artificial perspectives“ Achieving a widely accepted definition of human intelligence has been challenging, a situation mirrored by the diverse definitions of artificial intelligence in computer science. By critically examining published definitions, highlighting both consistencies and inconsistencies, this paper proposes a refined nomenclature that harmonizes conceptualizations across the two disciplines.…
-
Bayesian Models of Cognition
“Bayesian Models of Cognition Reverse Engineering the Mind” is a new MIT-press Open Access book available for online reading. The definitive introduction to Bayesian cognitive science, written by pioneers of the field. How does human intelligence work, in engineering terms? How do our minds get so much from so little? Bayesian models of cognition provide…
-
KNOWLEDGE ACQUISITION hindered by KNOWLEDGE ENTROPY DECAY during language model pretraining
This paper describes how a model’s tendency to broadly integrate its parametric knowledge evolves throughout pretraining, and how this behavior affects overall performance, particularly in terms of knowledge acquisition and forgetting. The concept of knowledge entropy is introduced, which quantifies the range of memory sources the model engages with; high knowledge entropy indicates that the…
Surtil : 