A composite holographic associative recall model

By Janet Metcalfe. 1982

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

Measuring Catastrophic Forgetting in Neural Networks (2017, background): “CHARM and TODAM are also convolution-correlation models that use internal codings to ensure that new input representations remain orthogonal to one another (Murdock 1983; Eich 1982).”
Similarity, global matching, and judgments of frequency (2001, background): “In global-matching models of recognition memory (Eich, 1982; Gillund & Shiffrin, 1984; Hintzman, 1988; Humphreys, Bain, & Pike, 1989; Murdock, 1982), a retrieval cue does not isolate a specific memory trace, but rather activates many traces simultaneously, each to a degree depending on its similarit”
Semantic Compositionality through Recursive Matrix-Vector Spaces (2012, background): “Mitchell and Lap-ata (2010) present an overview of the most important compositional models, from simple vector addition and component-wise multiplication to tensor products, and convolution (Metcalfe, 1990).”
Composition in Distributional Models of Semantics (2010, background): “These include tensor products (Smolensky, 1990), recursive distributed representations (RAAMS, Pollack, 1990), spatter codes (Kanerva, 1988), holographic reduced representations (Plate, 1995), and convolution (Metcalfe, 1990).”
The Feeling of Familiarity as a Regulator of Persuasive Processing (2001, background): “…initial bottom-up processing occurs with an “ease” or “fluency” that results in an (implicit) feeling of “similarity,” “recognition,” or “familiarity” (Eich, 1982; Fiske, 1982; Gillund & Siffrin, 1984; Higgins, 1989; Hintzman, 1988; Humphreys, Bain, & Pike, 1989; Jacoby & Dallas, 1981;…”
Holographic Reduced Representations: Convolution Algebra for Compositional Distributed Representations (1991, methodology): “Researchers have used three solutions to this problem of growth with recursive associations -(a) limit the depth of composition (Smolensky 1990]), (b) discard elements outside the n central ones (Metcalfe 1982]), and (c) use innnite vectors (Murdock 1982]).”
Memory is More than just Remembering: Strategic Control of Encoding, Accessing Memory, and Making Decisions (2007, background): “…the nature of its flexibility and not just its fallibility—is well accounted for by models that postulate distributed representations and memory access to a large set of memory traces in parallel (Eich, 1982; Hintzman, 1986; Murdock, 1993; ShiVrin & Steyvers, 1997), a process often termed matching.”
Recursive deep learning for natural language processing and computer vision (2014, unknown): “two-word phrases and analyze similarities computed by vector addition, multiplication, convolution (Metcalfe, 1990) and others.”
Environmental context-dependent memory: A review and meta-analysis (2001, methodology): “, Farnsworth, 1934; Reed, 1931), and real concern about the reliability of laboratory context effects began to appear in the published literature only more recently. Smith, Glenberg, and Bjork (1978) found that environmental context manipulations did not affect recognition memory, even though there ”
THE EFFECTS OF PERSONAL RELEVANCE AND REPETITION ON PERSUASIVE PROCESSING (2004, methodology): “In contrast to these findings, Garcia–Marques and Mackie (2001) demonstrated that repeated persuasive messages are processed less analytically than those that are not. In the first of two experiments, participants were presented with a message that opposed the implementation of governmentally enforc”
Vector-based Models of Semantic Composition (2008, background): “representations (RAAMS, Pollack, 1990), spatter codes (Kanerva, 1988), holographic reduced representations (Plate, 1995), and convolution (Metcalfe, 1990).”
A Solution to Plato's Problem: The Latent Semantic Analysis Theory of Acquisition, Induction, and Representation of Knowledge. (1997, unknown): “…learning and other psychological phenomena have employed vector representations and linear combination operations on them to good effect (e.g., Eich, 1982; Estes, 1986; Hintzman, 1986; Murdock, 1993), and many semantic network-represented theories, such as Kintsch (1988), could easily be…”