RECORD
Neural network model with discrete and continuous information representation
Neurons and Cognition · Submitted 20 Mar 2009
abstract compiled · 2026-09-23 · no language-model review
The authors' main claim In the present study, we propose a neural network model that achieves discrete and continuous information representation.
The compiled record
The paper's own sentences, arranged. Each label is drawn from a closed vocabulary; the number beside it is the probability the classifier gave that label. Numbers in the tables are the authors', checked by code. No sentence in this record was written by a model.
Open the compiled record
The abstract, sentence by sentence
An associative memory model and a neural network model with a Mexican-hat type interaction are the two most typical attractor networks used in the artificial neural network models. The associative memory model has discretely distributed fixed-point attractors, and achieves a discrete information representation. On the other hand, a neural network model with a Mexican-hat type interaction uses a line attractor to achieves a continuous information representation, which can be seen in the working memory in the prefrontal cortex and columnar activity in the visual cortex. In the present study, we propose a neural network model that achieves discrete and continuous information representation. We use a statistical-mechanical analysis to find that a localized retrieval phase exists in the proposed model, where the memory pattern is retrieved in the localized subpopulation of the network. In the localized retrieval phase, the discrete and continuous information representation is achieved by using the orthogonality of the memory patterns and the neutral stability of fixed points along the positions of the localized retrieval. The obtained phase diagram suggests that the antiferromagnetic interaction and the external field are important for generating the localized retrieval phase.
background contribution method result interpretation main claim
| # | sentence | role | the authors' own work | states the main conclusion | strength |
|---|---|---|---|---|---|
| s0 | An associative memory model and a neural network model with a Mexican-hat type interaction are the two most typical attractor networks used in the artificial neural network models. | background 1.00 | 0.03 | 0.02 | asserted 1.00 |
| s1 | The associative memory model has discretely distributed fixed-point attractors, and achieves a discrete information representation. | background 1.00 | 0.05 | 0.03 | asserted 1.00 |
| s2 | On the other hand, a neural network model with a Mexican-hat type interaction uses a line attractor to achieves a continuous information representation, which can be seen in the working memory in the prefrontal cortex and columnar activity in the visual cortex. | background 1.00 | 0.06 | 0.03 | asserted 0.97 |
| s3 | In the present study, we propose a neural network model that achieves discrete and continuous information representation. | contribution 1.00 | 0.82 | 0.30 | asserted 1.00 |
| s4 | We use a statistical-mechanical analysis to find that a localized retrieval phase exists in the proposed model, where the memory pattern is retrieved in the localized subpopulation of the network. | result 0.81 | 0.96 | 0.18 | asserted 1.00 |
| s5 | In the localized retrieval phase, the discrete and continuous information representation is achieved by using the orthogonality of the memory patterns and the neutral stability of fixed points along the positions of the localized retrieval. | interpretation 0.69 | 0.80 | 0.35 | asserted 1.00 |
| s6 | The obtained phase diagram suggests that the antiferromagnetic interaction and the external field are important for generating the localized retrieval phase. | result 0.73 | 0.89 | 0.22 | hedged possibility 0.93 |
What was examined, and what was not
- arXiv listing abstract v1
- full text
- figures and tables
- references and citing sentences
- relations to other papers
- P abstract
- S sections
- T body sentences
- C citations
- R cross-paper relations
The paper
Original abstract
An associative memory model and a neural network model with a Mexican-hat type interaction are the two most typical attractor networks used in the artificial neural network models. The associative memory model has discretely distributed fixed-point attractors, and achieves a discrete information representation. On the other hand, a neural network model with a Mexican-hat type interaction uses a line attractor to achieves a continuous information representation, which can be seen in the working memory in the prefrontal cortex and columnar activity in the visual cortex. In the present study, we propose a neural network model that achieves discrete and continuous information representation. We use a statistical-mechanical analysis to find that a localized retrieval phase exists in the proposed model, where the memory pattern is retrieved in the localized subpopulation of the network. In the localized retrieval phase, the discrete and continuous information representation is achieved by using the orthogonality of the memory patterns and the neutral stability of fixed points along the positions of the localized retrieval. The obtained phase diagram suggests that the antiferromagnetic interaction and the external field are important for generating the localized retrieval phase.
Human review
Discussion
Know something about this paper? Leave a comment, or highlight any passage above to comment on it.