Long sequence Hopfield memory
H Chaudhry, J Zavatone-Veth… - Advances in Neural …, 2024 - proceedings.neurips.cc
Sequence memory is an essential attribute of natural and artificial intelligence that enables
agents to encode, store, and retrieve complex sequences of stimuli and actions …
agents to encode, store, and retrieve complex sequences of stimuli and actions …
Virtual memories and massive generalization in connectionist combinatorial learning
O Brousse, P Smolensky - 11th Annual Conference Cognitive …, 2014 - taylorfrancis.com
We report a series of experiments on connectionist learning that addresses a particularly
pressing set of objections to the plausibility of connectionist learning as a model of human …
pressing set of objections to the plausibility of connectionist learning as a model of human …
Self-refreshing memory in artificial neural networks: Learning temporal sequences without catastrophic forgetting
While humans forget gradually, highly distributed connectionist networks forget
catastrophically: newly learned information often completely erases previously learned …
catastrophically: newly learned information often completely erases previously learned …
Metalearned neural memory
We augment recurrent neural networks with an external memory mechanism that builds
upon recent progress in metalearning. We conceptualize this memory as a rapidly adaptable …
upon recent progress in metalearning. We conceptualize this memory as a rapidly adaptable …
Learning rules for aversive associative memory formation
T Ozawa, JP Johansen - Current opinion in neurobiology, 2018 - Elsevier
Highlights•Depolarization and neuromodulatory signaling in the amygdala instructs fear
learning.•Midbrain and locus coeruleus pathways convey aversive instructive signals to …
learning.•Midbrain and locus coeruleus pathways convey aversive instructive signals to …
Associative long short-term memory
I Danihelka, G Wayne, B Uria… - International …, 2016 - proceedings.mlr.press
We investigate a new method to augment recurrent neural networks with extra memory
without increasing the number of network parameters. The system has an associative …
without increasing the number of network parameters. The system has an associative …
Free association in a neural network.
Free association among words is a fundamental and ubiquitous memory task. Although
distributed semantics (DS) models can predict the association between pairs of words, and …
distributed semantics (DS) models can predict the association between pairs of words, and …
Contextualized non-local neural networks for sequence learning
Recently, a large number of neural mechanisms and models have been proposed for
sequence learning, of which selfattention, as exemplified by the Transformer model, and …
sequence learning, of which selfattention, as exemplified by the Transformer model, and …
Recursive auto-associative memory: Devising compositional distributed representations
J Pollack - Proceedings of the tenth annual conference of the …, 1988 - books.google.com
A major outstanding problem for connectionist models is the representation of variablesized
recursive and sequential data structures, such as trees and stacks, in fixed-resource …
recursive and sequential data structures, such as trees and stacks, in fixed-resource …