Vector symbolic architectures are a viable alternative for Jackendoff's challenges

Gayler, Ross W.

doi:10.1017/s0140525x06309028

Cited by 41 publications

(38 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…One of the fundamental aims of neuroscience is to comprehend how the brain manages to process signals from the outside world into a coherent informational universe that allows us to survive and prosper. In human cognition, the existence of language adds a new and novel codification strategy, one in which conceptual constructions are mapped onto words (Gayler 2006).…”

Section: Discussionmentioning

confidence: 99%

Modeling spatial–temporal operations with context-dependent associative memories

Mizraji

Lin

2015

Cogn Neurodyn

View full text Add to dashboard Cite

We organize our behavior and store structured information with many procedures that require the coding of spatial and temporal order in specific neural modules. In the simplest cases, spatial and temporal relations are condensed in prepositions like "below" and "above", "behind" and "in front of", or "before" and "after", etc. Neural operators lie beneath these words, sharing some similarities with logical gates that compute spatial and temporal asymmetric relations. We show how these operators can be modeled by means of neural matrix memories acting on Kronecker tensor products of vectors. The complexity of these memories is further enhanced by their ability to store episodes unfolding in space and time. How does the brain scale up from the raw plasticity of contingent episodic memories to the apparent stable connectivity of large neural networks? We clarify this transition by analyzing a model that flexibly codes episodic spatial and temporal structures into contextual markers capable of linking different memory modules.

show abstract

Section: Discussionmentioning

confidence: 99%

Modeling spatial–temporal operations with context-dependent associative memories

Mizraji

Lin

2015

Cogn Neurodyn

View full text Add to dashboard Cite

show abstract

“…The vector components can be binary, ternary, real, or complex values [82,83]. In our experiments, we use 32,000 dimensional binary vectors constructed in accordance with the Binary Spatter Code (BSC) [84], one of a family of representational approaches known as Vector Symbolic Architectures (VSAs) [84–87]. This dimensionality was selected based on the results of simulation experiments in previous research [88], which suggest that at this dimensionality around 2000 unique elemental vectors can be superposed with low probability of the superposed product being closer to some other elemental vector in the space than its component vectors.…”

Section: Methodsmentioning

confidence: 99%

“…Binding (⊗) is a compositional operation that is provided by VSAs, such as the BSC [86,87]. Binding two elemental vectors generates a third vector, which is dissimilar from these two component vectors.…”

Section: Methodsmentioning

confidence: 99%

Identifying plausible adverse drug reactions using knowledge extracted from the literature

Shang

Rindflesch

et al. 2014

Journal of Biomedical Informatics

View full text Add to dashboard Cite

Pharmacovigilance involves continually monitoring drug safety after drugs are put to market. To aid this process; algorithms for the identification of strongly correlated drug/adverse drug reaction (ADR) pairs from data sources such as adverse event reporting systems or Electronic Health Records have been developed. These methods are generally statistical in nature, and do not draw upon the large volumes of knowledge embedded in the biomedical literature. In this paper, we investigate the ability of scalable Literature Based Discovery (LBD) methods to identify side effects of pharmaceutical agents. The advantage of LBD methods is that they can provide evidence from the literature to support the plausibility of a drug/ ADR association, thereby assisting human review to validate the signal, which is an essential component of pharmacovigilance. To do so, we draw upon vast repositories of knowledge that has been extracted from the biomedical literature by two Natural Language Processing tools, MetaMap and SemRep. We evaluate two LBD methods that scale comfortably to the volume of knowledge available in these repositories. Specifically, we evaluate Reflective Random Indexing (RRI), a model based on concept-level co-occurrence, and Predication-based Semantic Indexing (PSI), a model that encodes the nature of the relationship between concepts to support reasoning analogically about drug-effect relationships. An evaluation set was constructed from the Side Effect Resource 2 (SIDER2), which contains known drug/ADR relations, and models were evaluated for their ability to “rediscover” these relations. In this paper, we demonstrate that both RRI and PSI can recover known drug-adverse event associations. However, PSI performed better overall, and has the additional advantage of being able to recover the literature underlying the reasoning pathways it used to make its predictions.

show abstract

“…Treves, 2005), does not advance our understanding of the computational question, how can compositional structures be processed at the neuronal level. Various exciting proposals have been put forward (Pulvermü ller, 2002;van der Velde and de Kamps, 2006;Gayler, 2003Gayler, , 2006Eliasmith and Thagard, 2001;Hashimoto, 2008), often as neuronal mechanisms for identifying syntactic structure, but they do not yet satisfactorily solve the problem of matching semantic with syntactic representations, and thus leave open the question of how to match meanings with neural representations. Again, the core issue is what neural mechanisms can facilitate compositional interpretation, and it appears necessary to address it using model systems of sufficient complexity, where solutions can be imagined to scale up to real-life problems.…”

Section: Compositionality Can Only Be Analysed In Sufficiently Large mentioning

confidence: 99%

Computational constraints on compositional interpretation: Refocusing the debate on language universals

Rothstein¹,

Treves²

2010

Lingua

View full text Add to dashboard Cite

Vector symbolic architectures are a viable alternative for Jackendoff's challenges

Cited by 41 publications

References 28 publications

Modeling spatial–temporal operations with context-dependent associative memories

Modeling spatial–temporal operations with context-dependent associative memories

Identifying plausible adverse drug reactions using knowledge extracted from the literature

Computational constraints on compositional interpretation: Refocusing the debate on language universals

Contact Info

Product

Resources

About