Mapping Part-Whole Hierarchies into Connectionist Networks

By Geoffrey E. Hinton. 1990

How researchers see this paper

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

In Model Architectures

Citations in the corpus

Recursive Deep Models for Semantic Compositionality Over a Sentiment Treebank (2013, background): “Apart from the above mentioned work on RNNs, several compositionality ideas re-lated to neural networks have been discussed by Bot-tou (2011) and Hinton (1990) and ﬁrst models such as Recursive Auto-associative memories been experimented with by Pollack (1990).”
Relational inductive biases, deep learning, and graph networks (2018, background): “…connectionist (Rumelhart et al., 1987) forebears were faced with analogous critiques from structured, symbolic positions (Fodor and Pylyshyn, 1988; Pinker and Prince, 1988), there was a constructive eﬀort (Bobrow and Hinton, 1990; Marcus, 2001) to address the challenges directly and carefully.”
How to Represent Part-Whole Hierarchies in a Neural Network (2021, background): “The way to handle such an enormous range is to have a ﬂexible mapping between entities in the world and the levels of GLOM [Hinton, 1990].”
Deep Learning: Methods and Applications (2014, background): “, they can potentially perform powerful reasoning over structures, as argued in various historical publications as well as recent essays [38, 156, 286, 288, 292, 336, 335].”
From machine learning to machine reasoning (2011, background): “Comparable ideas have been proposed by Hinton (1990).”
Binary Spatter-Coding of Ordered K-Tuples (1996, background): “What that means, is discussed in depth by Hinton (1990) .”
Rule Extraction from Recurrent Neural Networks: ATaxonomy and Review (2005, methodology): “A brief (and most probably inconclusive) list of examples of other analysis tools that have been used on RNNs is: Hinton diagrams (e.g. Hinton 1990, Niklasson & Bod´en 1997), Hierarchical Cluster Analysis (e.g. Cleeremans, McClelland & Servan-Schreiber 1989, Elman 1990, Servan-Schreiber, Cleeremans…”
Learning Recursive Distributed Representations for Holistic Computation (1991, methodology): “As with the dual-ported RAAM in Figure 4, while con(cid:13)uent inference is turned on, the representation for a problem and its answer are treated as if they share the same representation space as shown in Figure 13(a).”
Semantic Compositionality through Recursive Matrix-Vector Spaces (2012, background): “Bottou (2011) and Hinton (1990) discussed related models such as recursive autoencoders for text understanding.”
Composition in Distributional Models of Semantics (2010, background): “Hinton (1990) makes clear that one of the strengths of symbolic representations is the handling of structures of unbounded complexity, and discusses how this might be implemented in terms of fixed dimensionality connectionist representations.”
Hyperdimensional Computing: An Introduction to Computing in Distributed Representation with High-Dimensional Random Vectors (2009, background): “In it Hinton [11] argues for the necessity of a reduced representation if structured information such as hierarchies”