Associative memory

By J. Austin. 1987

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

Deep learning in neural networks: An overview (2014, background): “…simple NNs trained by SL (e.g., Narendra & Thathatchar, 1974; Rosenblatt, 1958, 1962; Widrow & Hoff, 1962) and UL (e.g., Grossberg, 1969; Kohonen, 1972; von der Malsburg, 1973; Willshaw & von der Malsburg, 1976), as well as closely related associative memories (e.g., Hopfield, 1982; Palm, 1980).”
Accelerated Learning in Back-propagation Nets (1989, unknown): “We want to relate this work to some results given by Palm in (Palm, 1980).”
Using Conceptors to Manage Neural Long-Term Memories for Temporal Patterns (2017, background): “The paradigmatic model of a neural LTM is the associative memory pioneered, among others, by Willshaw et al. (1969), Cooper (1973), Kohonen (1974), Palm (1980) and Hopfield (1982).”
Forming sparse representations by local anti-Hebbian learning (1990, background): “The capacity of an associative memory network, i.e. the number of input-output pairs that can be stored using a highly distributed representation is significantly lower than optimal (Willshaw et al. 1969; Palm 1980).”
Unsupervised Learning of Invariant Representations in Hierarchical Architectures (2013, background): “Retrieving from an associative memory: optimal sparse encoding and recall There are interesting estimates of optimal properties of codes for associative memories, including optimal sparsness (see [71, 76]).”
Controlling Recurrent Neural Networks by Conceptors (2014, background): “This idea can be traced back at least to the notion of cell assemblies formulated by Hebb [45], reached a first culmination in the formal analysis of associative memories [80, 48, 4], and has since then diversified into a range of increasingly complex models of interacting (partial) neural attractor”
Associative Data Storage and Retrieval in Neural Networks (1996, methodology): “Using a practically unrealistic xed-point read-out scheme7 and the Hebb rule we have found completion capacity values of C = 0:36 bits/syn for incremental and C = 0:35 bits/syn for binary storage [30, 23].”
Storage capacity diverges with synaptic efficiency in an associative memory model with synaptic delay and pruning (2003, background): “Particularly in the case of correlation-type associative memory [1]–[5], models with randomly pruned synapses have been discussed in detail [6]–[11].”
Improved bidirectional retrieval of sparse patterns stored by Hebbian learning (1999, unknown): “NAM models have been proposed for efficient searching in large data-bases allowing fast, fault-tolerant access and being particularly well-suited for parallel implementations (Steinbuch, 1961; Kohonen, 1977; Bentz et al., 1989).”
Face recognition by independent component analysis (2002, background): “Networks with sparse inputs can store more memories and provide more effective retrieval with partial information [10], [47].”
What Is the Goal of Sensory Coding? (1994, background): “Several authors have noted that when the inputs to the networks are sparse, the networks can store more memories and provide more effective retrieval with partial information (Palm 1980; Baum et al. 1988).”
Linear Transformers Are Secretly Fast Weight Programmers (2021, background): “…memory can be found in numerous works since Hebb’s informal rule (Hebb, 1949) and its more concrete formal variants (Steinbuch, 1961; Steinbuch & Piske, 1963; Kohonen, 1972; Palm, 1980) including Hopﬁeld networks (Hopﬁeld, 1982; Little, 1974) and bi-directional associative nets (Kosko, 1988).”