A simple neural network generating an interactive memory

By James A. Anderson. 1972

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

Locating and Editing Factual Associations in GPT (2022, methodology): “We view W (l) proj as a linear associative memory (Kohonen, 1972; Anderson, 1972).”
Mass-Editing Memory in a Transformer (2022, background): “(2022) have proposed editing methods that alter sparse sets of neurons, but we adopt the classical view of a linear layer as an associative memory (Anderson, 1972; Kohonen, 1972).”
Moving the Eiffel Tower to ROME: Tracing and Editing Facts in GPT (2021, background): “The linear associative memory view of a single 326 linear layer is a classical model (Kohonen, 1972; 327 Anderson, 1972) that notes that any linear operation”
Locating and Editing Factual Knowledge in GPT (2022, methodology): “To reason about these structures, we view W ( l ) proj as a linear associative memory (Kohonen, 1972; Anderson, 1972).”
Laminar selectivity of the cholinergic suppression of synaptic transmission in rat hippocampal region CA1: computational modeling and brain slice physiology (1994, background): “…the learned capacity for a specific pattern of activity in one population of cortical neurons to elicit an associated pattern of activity in another population of cortical neurons (Grossberg, 1970; Anderson, 1972, 1983; Amit, 1988; Kohonen, 1988; Hasselmo et al., 1992; Hasselmo, 1993, 1994).”
Hyperdimensional Computing: An Introduction to Computing in Distributed Representation with High-Dimensional Random Vectors (2009, methodology): “The early models were the linear correlation-matrix memories of Anderson [1] and Kohonen [2] that equate stored patterns with the eigenvectors of the memory (weight) matrix.”
MACE: Mass Concept Erasure in Diffusion Models (2024, methodology): “Drawing upon methods that view matrices as linear associative memories [1, 28], often used to edit knowledge embedded within neural networks [2, 4, 5, 17, 36, 37, 43], we formulate our objective function as follows: where λ 1 ∈ R + is a hyperparameter, e is the embedding of a word co-existing with…”
Connectionist models of recognition memory: constraints imposed by learning and forgetting functions. (1990, background): “Although there has been work on such neurally inspired models for several years (e.g., J. A. Anderson, 1972, 1973; J. A. Anderson & Hinton, 1981; J. A. Anderson, Silverstein, Ritz, & Jones, 1977; Grossberg , 1980, 1988; Kohonen, 1978), recent interest has been fueled by the finding that earlier…”
Synaptic Plasticity Forms and Functions. (2020, background): “Here, inputs driving a given output will have their connection strengths enhanced,forming a simple association that allows even fragments of the associated input pattern to evoke the correct output activity (Andersen 1972, Kohonen 1972, Hopfield 1982).”
Associative Data Storage and Retrieval in Neural Networks (1996, methodology): “Models with linear transfer function, as for instance proposed in Kohonen [16] or Anderson [21, 22], lead for large networks to quasi continous valued output patterns.”
A History of Spike-Timing-Dependent Plasticity (2011, background): “, Anderson, P., and Bliss, T. V. (1993). Failure to induce long-term depression by an anti-correlation procedure in area CA1 of the rat hippocampal slice. Eur. J. Neurosci. 5, 1241–1246. Pavlov, I. P. (1897). The Work of the Digestive Glands English Translation by W. H. Thompson, London, 1902. (Lond”
Merging chrominance and luminance in early, medium, and late fusion using Convolutional Neural Networks (2015, background): “Anderson36 got published “A simple neural network generating an interactive memory” with a more biological connotation [Anderson, 1972].”