Parallel Distributed Processing: Explorations in the Microstructures of Cognition

By Geoffrey Sampson, David E. Rumelhart, James L. McClelland. 1987

Subfields: Neuroscience, Cognitive Science & Psychology

How researchers see this paper

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

In Neuroscience

In Cognitive Science & Psychology

Citations in the corpus

Effectiveness of self-supervised pre-training for speech recognition (2019, background): “Representation learning has been an active research area for more than 30 years (Hinton et al., 1986), with the goal of learning high level representations which separates different explanatory factors of the phenomena represented by the input data (LeCun et al., 2015; Bengio et al., 2013).”
The Graph Neural Network Model (2009, positive): “Moreover, we will assume that there exist two procedures and , which implement the forward phase and the backward phase of the backpropagation procedure [71], respectively.”
Neural Programmer-Interpreters (2015, background): “For example, the idea of using dynamically programmable networks in which the activations of one network become the weights (the program) of a second network was mentioned in the Sigma-Pi units section of the inﬂuential PDP paper (Rumelhart et al., 1986).”
Reinforcement Learning: A Survey (1996, methodology): “Popular techniques include various neural-network methods (Rumelhart & McClelland, 1986), fuzzy logic (Berenji, 1991; Lee, 1991).”
Exploring Randomly Wired Neural Networks for Image Recognition (2019, background): “What we call deep learning today descends from the connectionist approach to cognitive science [38, 7]—a paradigm reflecting the hypothesis that how computational networks are wired is crucial for building intelligent machines.”
Stabilizing Transformers for Reinforcement Learning (2019, background): “…with other existing proposals (Krause et al., 2016; Kalchbrenner et al., 2015; Wu et al., 2016), as well as works trying to discover optimal gating by neural architecture search (Zoph & Le, 2017) More generally, gating and multiplicative interactions have a long history (Rumelhart et al., 1986).”
Learning to Match using Local and Distributed Representations of Text for Web Search (2016, background): “The main disadvantage of term matching is that related terms are ignored, so when ranking for the query ‘Australia’ then only the term frequency of ‘Australia’ is considered, even though counting terms like ‘Sydney’ and ‘koala’ can be good positive evidence.”
Attention and choice: a review on eye movements in decision making. (2013, methodology): “The PCS model has been implemented in neural networks that simulate the coherence maximization process (Glöckner & Betsch, 2008; Glöckner & Herbold, 2011; Kunda & Thagard, 1996; Read, Vanman, & Miller, 1997; Rumelhart & McClelland, 1986).”
Natural- to formal-language generation using Tensor Product Representations (2019, methodology): “TP-N2F is trained using back-propagation (Rumelhart et al., 1986) with the Adam optimizer (Kingma & Ba, 2017) and teacher-forcing.”
Implicit learning and consciousness: A graded, dynamic perspective (2002, unknown): “Consistently with well-known ideas in the connectionist literature (e.g., Rumelhart & McClelland, 1986), we will assume the following without further discussion: each other's processing in a graded manner that depends on the strength of the connection between them and on the strength of the…”
FROM FACTORS TO ACTORS: Computational Sociology and Agent-Based Modeling (2002, background): “Artificial neural networks are a simple type of self-programmable learning device based on parallel distributed processing (Rummelhart and McClelland 1988) and modeled after the nerve systems of living organisms.”