Sequence disambiguation and pattern completion by cooperation between autoassociative and heteroassociative memories of functionally divided hippocampal CA3

Samura, Toshikazu; Hattori, Motonobu; Ishizaki, Shun

doi:10.1016/j.neucom.2008.04.026

Cited by 17 publications

(16 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In previous work, we have proposed a modular network model of associative memory [8] grounded on biological data [1,17]. These data report heterogeneities in the hippocampal structure that might support the coexistence of autoassociative and heteroassociative networks in this region.…”

Section: Introductionmentioning

confidence: 88%

A Modular Network Architecture Resolving Memory Interference Through Inhibition

Kassab

Alexandre

2016

Studies in Computational Intelligence

View full text Add to dashboard Cite

In real learning paradigms like pavlovian conditioning, several modes of learning are associated, including generalization from cues and integration of specific cases in context. Associative memories have been shown to be interesting neuronal models to learn quickly specific cases but they are hardly used in realistic applications because of their limited storage capacities resulting in interferences when too many examples are considered. Inspired by biological considerations, we propose a modular model of associative memory including mechanisms to manipulate properly multimodal inputs and to detect and manage interferences. This paper reports experiments that demonstrate the good behavior of the model in a wide series of simulations and discusses its impact both in machine learning and in biological modeling.

show abstract

Section: Introductionmentioning

confidence: 88%

A Modular Network Architecture Resolving Memory Interference Through Inhibition

Kassab

Alexandre

2016

Studies in Computational Intelligence

View full text Add to dashboard Cite

show abstract

“…In a recent work, we have proposed a refinement of hippocampal model (Kassab and Alexandre, 2015), inspired from recent biological data (Samura et al, 2008). These data report heterogeneities in the hippocampal structure that might support the coexistence of autoassociative and heteroassociative memories in this region.…”

Section: Introductionmentioning

confidence: 89%

A Heteroassociative Learning Model Robust to Interference

Kassab

Alexandre

2015

Proceedings of the 7th International Joint Conference on Computational Intelligence

View full text Add to dashboard Cite

Neuronal models of associative memories are recurrent networks able to learn quickly patterns as stable states of the network. Their main acknowledged weakness is related to catastrophic interference when too many or too close examples are stored. Based on biological data we have recently proposed a model resistant to some kinds of interferences related to heteroassociative learning. In this paper we report numerical experiments that highlight this robustness and demonstrate very good performances of memorization. We also discuss convergence of interests for such an adaptive mechanism for biological modeling and information processing in the domain of machine learning.

show abstract

“…While effective, such networks require another complete layer to keep a dynamical memory, an approach judged to be inefficient. To address this issue, context codes with less overhead have been proposed where, instead of a network, the state of a unit or a collection of units is determined by the dynamical history of the system and that state is then used for disambiguation (Sohal and Hasselmo, 1998;Samura et al, 2008). In our network, disambiguation can be achieved by building cell assemblies containing a subset of units that are preferentially connected to the subsequent assembly in the sequence.…”

Section: Sequence Disambiguation and Overlapping Representationsmentioning

confidence: 99%

Probabilistic associative learning suffices for learning the temporal structure of multiple sequences

Martínez

Lansner

Herman

2019

Preprint

View full text Add to dashboard Cite

Many brain phenomena both at the cognitive and behavior level exhibit remarkable sequential characteristics. While the mechanisms behind the sequential nature of the underlying brain activity are likely multifarious and multi-scale, in this work we attempt to characterize to what degree some of this properties can be explained as a consequence of simple associative learning. To this end, we employ a parsimonious firing-rate attractor network equipped with the Hebbian-like Bayesian Confidence Propagating Neural Network (BCPNN) learning rule relying on synaptic traces with asymmetric temporal characteristics. The proposed network model is able to encode and reproduce temporal aspects of the input, and offers internal control of the recall dynamics by gain modulation. We provide an analytical characterisation of the relationship between the structure of the weight matrix, the dynamical network parameters and the temporal aspects of sequence recall. We also present a computational study of the performance of the system under the effects of noise for an extensive region of the parameter space. Finally, we show how the inclusion of modularity in our network structure facilitates the learning and recall of multiple overlapping sequences even in a noisy regime.

show abstract

Sequence disambiguation and pattern completion by cooperation between autoassociative and heteroassociative memories of functionally divided hippocampal CA3

Cited by 17 publications

References 19 publications

A Modular Network Architecture Resolving Memory Interference Through Inhibition

A Modular Network Architecture Resolving Memory Interference Through Inhibition

A Heteroassociative Learning Model Robust to Interference

Probabilistic associative learning suffices for learning the temporal structure of multiple sequences

Contact Info

Product

Resources

About