Creating hierarchical categories using cell assemblies

The 2011 International Joint Conference on Neural Networks

2011

Abstract-One of the main tasks in Information Retrieval is to match a user query to the documents that are relevant for it. This matching is challenging because in many cases the keywords the user chooses will be different from the words the authors of the relevant documents have used. Throughout the years, many approaches have been proposed to deal with this problem. One of the most popular consists in expanding the query with related terms with the goal of retrieving more relevant documents. In this paper, we propose a new method in which a Cell Assembly model is applied for query expansion. Cell Assemblies are reverberating circuits of neurons that can persist long beyond the initial stimulus has ceased. They learn through Hebbian Learning rules and have been used to simulate the formation and the usage of human concepts. We adapted the Cell Assembly model to learn relationships between the terms in a document collection. These relationships are then used to augment the original queries. Our experiments use standard Information Retrieval test collections and show that some queries significantly improved their results with our technique.

Section: Cell Assembly Modelmentioning

confidence: 99%

“…The CA Network Model uses fatiguing Leaky Integrate and Fire (fLIF) neurons described briefly in section III-A (and more completely in [12]). The neurons are connected by synapses that learn according to Hebbian rules described briefly in section III-B (and more completely in [12]).…”

Section: Cell Assembly Modelmentioning

confidence: 99%

Cell assemblies for query expansion in Information Retrieval

Volpe

Moreira

The 2011 International Joint Conference on Neural Networks

2011

“…A brief description of the fLIF model is given below, and a more detailed one can be found elsewhere (Huyck 1999(Huyck , 2007. In the Integrate and Fire model, a neuron collects activation from other neurons, and fires when it has sufficient activation to surpass a threshold h. When the neuron fires, it sends activation to each neuron to which it has synapses, and the activation is directly proportional to the weight associated with each synapse.…”

Section: The Neural Modelmentioning

confidence: 99%

“…For verbs, this hierarchy is derived from a verb hierarchy available locally. This type of hierarchical encoding can be learned (Huyck 2007), but for reasons of technological expediency when implementing it on a PC, CABot2 had its hierarchical encoding hard-coded.…”

Section: Input Access and Semanticsmentioning

confidence: 99%

A psycholinguistic model of natural language parsing implemented in simulated neurons

2009

Cogn Neurodyn

Self 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.

“…It forces the total synaptic strength leaving a neuron towards the desired weight, W B . Elsewhere (Huyck 2007), this learning mechanism has been used to learn hierarchical categories where categories share neurons. Compensatory learning is biologically plausible because the overall activation a neuron can emit is limited.…”

Section: Number Subnetmentioning

confidence: 99%

Variable binding by synaptic strength change

2009

Connection Science

Self 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.