An Associative Model of Cortical Language and Action Processing

Knoblauch, Andreas; Markert, Heiner; Palm, Guenther

doi:10.1142/9789812701886_0007

Cited by 8 publications

(4 citation statements)

References 3 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Adding the biologically plausible mechanism of threshold control [25], Palm's group has built models with high explanatory capability that view the cortex as a group of associative memories. This type of idea has been applied for instance to language understanding [26,27]. And, by the nature of the associative memory model, it has led to widely confirmed neuroscientific predictions.…”

Section: Neural Assemblies Via Associative Memorymentioning

confidence: 96%

Competitive learning to generate sparse representations for associative memory

Sacouto¹,

Wichert²

2023

Preprint

View full text Add to dashboard Cite

One of the most well established brain principles, hebbian learning, has led to the theoretical concept of neural assemblies. Based on it, many interesting brain theories have spawned. Palm's work implements this concept through binary associative memory, in a model that not only has a wide cognitive explanatory power but also makes neuroscientific predictions. Yet, associative memory can only work with logarithmic sparse representations, which makes it extremely difficult to apply the model to real data. We propose a biologically plausible network that encodes images into codes that are suitable for associative memory. It is organized into groups of neurons that specialize on local receptive fields, and learn through a competitive scheme. After conducting auto-and heteroassociation experiments on two visual data sets, we can conclude that our network not only beats sparse coding baselines, but also that it comes close to the performance achieved using optimal random codes.

show abstract

Section: Neural Assemblies Via Associative Memorymentioning

confidence: 96%

Competitive learning to generate sparse representations for associative memory

Sacouto¹,

Wichert²

2023

Preprint

View full text Add to dashboard Cite

show abstract

“…Even though it may be more difficult to develop systems based on models with direct links to neurons, there have been prior neural parsers. One such parser used a spiking neural model to parse a regular language (Knoblauch et al 2004). Importantly, like the CABot2 parser, this parser was embedded in an agent.…”

Section: Neural and Other Connectionist Parsersmentioning

confidence: 99%

A psycholinguistic model of natural language parsing implemented in simulated neurons

Huyck

2009

Cogn Neurodyn

View full text Add to dashboard Cite

A natural language parser implemented entirely in simulated neurons is described. It produces a semantic representation based on frames. It parses solely using simulated fatiguing Leaky Integrate and Fire neurons, that are a relatively accurate biological model that is simulated efficiently. The model works on discrete cycles that simulate 10 ms of biological time, so the parser has a simple mapping to psychological parsing time. Comparisons to human parsing studies show that the parser closely approximates this data. The parser makes use of Cell Assemblies and the semantics of lexical items is represented by overlapping hierarchical Cell Assemblies so that semantically related items share neurons. This semantic encoding is used to resolve prepositional phrase attachment ambiguities encountered during parsing. Consequently, the parser provides a neurally-based cognitive model of parsing.

show abstract

“…Networks of spiking neurons are used to segment a visual scene into different objects based on the firing timing of neurons associated with those objects (Knoblauch and Palm 2001); a scene with a triangle and a square is presented, and neurons associated with the square fire together and the triangle neurons fire together, but at different times from the square neurons. Spiking neurons are also used to parse simple text (Knoblauch, Markert, and Palm 2004) using binding via synchrony.…”

Section: Binding Via Synchronymentioning

confidence: 99%

Variable binding by synaptic strength change

Huyck

2009

Connection Science

View full text Add to dashboard Cite

Copyright and moral rights to this thesis/research project are retained by the author and/or other copyright owners. The work is supplied on the understanding that any use for commercial gain is strictly forbidden. A copy may be downloaded for personal, non-commercial, research or study without prior permission and without charge. Any use of the thesis/research project for private study or research must be properly acknowledged with reference to the work's full bibliographic details.This thesis/research project may not be reproduced in any format or medium, or extensive quotations taken from it, or its content changed in any way, without first obtaining permission in writing from the copyright holder(s).If you believe that any material held in the repository infringes copyright law, please contact the Repository Team at Middlesex University via the following email address:eprints@mdx.ac.ukThe item will be removed from the repository while any claim is being investigated. Journal …Connection ScienceArticle ID … CCOS395590 Variable binding is a difficult problem for neural networks. Two new mechanisms for binding by synaptic change are presented, and in both, bindings are erased and can be reused. The first is based on the commonly used learning mechanism of permanent change of synaptic weight, and the second on synaptic change which decays. Both are biologically motivated models. Simulations of binding on a paired association task are shown with the first mechanism succeeding with a 97.5% F-Score, and the second performing perfectly.Further simulations show that binding by decaying synaptic change copes with cross talk, and can be used for compositional semantics. It can be inferred that binding by permanent change accounts for these, but it faces the stability plasticity dilemma. Two other existing binding mechanisms, synchrony and active links, are compatible with these new mechanisms. All four mechanisms are compared and integrated in a Cell Assembly theory.

show abstract

An Associative Model of Cortical Language and Action Processing

Cited by 8 publications

References 3 publications

Competitive learning to generate sparse representations for associative memory

Competitive learning to generate sparse representations for associative memory

A psycholinguistic model of natural language parsing implemented in simulated neurons

Variable binding by synaptic strength change

Contact Info

Product

Resources

About