The evolution of mental models

By Astro Teller. 1994

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Citations in the corpus

Deep learning in neural networks: An overview (2014, neutral): “…& Jordan, 1995; Kaelbling et al., 1995; Kimura, Miyazaki, & Kobayashi, 1997; Lin, 1993; Littman, Cassandra, & Kaelbling, 1995; McCallum, 1996; Otsuka, Yoshimoto, & Doya, 2010; Ring, 1991, 1993, 1994; Schmidhuber, 1990d, 1991c; Teller, 1994; Wiering & Schmidhuber, 1996, 1998a; Williams, 1992a).”
On Learning to Think: Algorithmic Information Theory for Novel Combinations of Reinforcement Learning Controllers and Recurrent Neural World Models (2015, background): “This triggered work on partially observable Markov decision problems (POMDPs) [223, 222, 227, 204, 205, 206, 316, 148, 278, 122, 152, 25, 114, 160, 126, 308, 309, 183].”
HQ-Learning (1997, methodology): “Certain techniques for automatic programsynthesis based on evolutionary principles can be used to evolve short-term memorizing programsthat read and write MCs during runtime (e.g., Teller, 1994).”
Probabilistic Incremental Program Evolution (1997, background): “MCs are accessed by write and read functions that are added to F (see also Teller, 1994).”
GENETIC ALGORITHM: REVIEW AND APPLICATION (2010, unknown): “Teller (1994) introduced Indexed Memory to allow a selection from an arbitrary set of memory cells [11].”
Evolutionary computation for modeling and optimization (2005, background): “Tricky, isn’t it? In his paper “The Evolution of Mental Models” [55], Astro Teller added to his dozer control language a new type of structure called indexed memories.”