Hierarchical associative memory
D Krotov - arXiv preprint arXiv:2107.06446, 2021 - arxiv.org
Dense Associative Memories or Modern Hopfield Networks have many appealing properties
of associative memory. They can do pattern completion, store a large number of memories …
of associative memory. They can do pattern completion, store a large number of memories …
Large associative memory problem in neurobiology and machine learning
D Krotov, J Hopfield - arXiv preprint arXiv:2008.06996, 2020 - arxiv.org
Dense Associative Memories or modern Hopfield networks permit storage and reliable
retrieval of an exponentially large (in the dimension of feature space) number of memories …
retrieval of an exponentially large (in the dimension of feature space) number of memories …
[PDF][PDF] Learning large-scale heteroassociative memories in spiking neurons
AR Voelker, E Crawford… - … Computation and Natural …, 2014 - e2crawfo.github.io
Associative memories have been an active area of research over the last forty years
(Willshaw et al., 1969; Kohonen, 1972; Hopfield, 1982) because they form a central …
(Willshaw et al., 1969; Kohonen, 1972; Hopfield, 1982) because they form a central …
Universal hopfield networks: A general framework for single-shot associative memory models
A large number of neural network models of associative memory have been proposed in the
literature. These include the classical Hopfield networks (HNs), sparse distributed memories …
literature. These include the classical Hopfield networks (HNs), sparse distributed memories …
In search of dispersed memories: Generative diffusion models are associative memory networks
L Ambrogioni - arXiv preprint arXiv:2309.17290, 2023 - arxiv.org
Hopfield networks are widely used in neuroscience as simplified theoretical models of
biological associative memory. The original Hopfield networks store memories by encoding …
biological associative memory. The original Hopfield networks store memories by encoding …
Associative memories via predictive coding
Associative memories in the brain receive and store patterns of activity registered by the
sensory neurons, and are able to retrieve them when necessary. Due to their importance in …
sensory neurons, and are able to retrieve them when necessary. Due to their importance in …
Neural associative memory with optimal Bayesian learning
A Knoblauch - Neural Computation, 2011 - ieeexplore.ieee.org
Neural associative memories are perceptron-like single-layer networks with fast synaptic
learning typically storing discrete associations between pairs of neural activity patterns …
learning typically storing discrete associations between pairs of neural activity patterns …
Recurrent correlation associative memories: a feature space perspective
R Perfetti, E Ricci - IEEE Transactions on Neural Networks, 2008 - ieeexplore.ieee.org
In this paper, we analyze a model of recurrent kernel associative memory (RKAM) recently
proposed by Garcia and Moreno. We show that this model consists in a kernelization of the …
proposed by Garcia and Moreno. We show that this model consists in a kernelization of the …
Biological learning in key-value memory networks
D Tyulmankov, C Fang… - Advances in Neural …, 2021 - proceedings.neurips.cc
In neuroscience, classical Hopfield networks are the standard biologically plausible model
of long-term memory, relying on Hebbian plasticity for storage and attractor dynamics for …
of long-term memory, relying on Hebbian plasticity for storage and attractor dynamics for …
Auto-associative memory with two-stage dynamics of nonmonotonic neurons
HF Yanai, SI Amari - IEEE Transactions on Neural Networks, 1996 - ieeexplore.ieee.org
Dynamical properties of a neural auto-associative memory with two-stage neurons are
investigated theoretically. The two-stage neuron is a model whose output is determined by a …
investigated theoretically. The two-stage neuron is a model whose output is determined by a …