Parallel distributed processing: explorations in the microstructure of cognition, vol. 1: foundations

How researchers see this paper

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

Analysis Methods in Neural Language Processing: A Survey (2018, background): “Rumelhart and McClelland (1986) built a feed-forward neural network for learning the English past tense and analyzed its performance on a variety of examples and conditions.”
Reinforcement Learning: A Survey (1996, methodology): “Popular techniques include various neural-network methods (Rumelhart & McClelland, 1986), fuzzy logic (Berenji, 1991; Lee, 1991).”
Deep Learning for Symbolic Mathematics (2019, background): “A longstanding tradition in machine learning opposes rule-based inference to statistical learning (Rumelhart et al., 1986), and neural networks clearly stand on the statistical side.”
The hardware lottery (2020, background): “The essays argued persuasively that biological evidence suggested massive parallelism was needed to make deep neural network approaches work (Rumelhart et al., 1986).”
Rethinking eliminative connectionism. (1998, background): “In simulations, Prasada and Pinker found that although the Rumelhart and McClelland (1986) model can in some (though not all) circumstances apply generalizations to novel items that strongly resemble training items, it encountered difficulty when inflecting input words that lacked resemblance to…”