Loading...
Please wait, while we are loading the content...
Similar Documents
Evaluating hebbian self-organizing memories for lexical representation and access.
| Content Provider | CiteSeerX |
|---|---|
| Author | Marzi, Claudia |
| Abstract | The lexicon is the store of words in long-term memory. Any attempt at modelling lexical competence must take issues of string storage seriously. In the present contribution, we discuss a few desiderata that any biologically-inspired computational model of the mental lexicon has to meet, and detail a multi-task evaluation protocol for their assessment. The proposed protocol is applied to a novel computational architecture for lexical storage and acquisition, the “Topological Temporal Hebbian SOMs ” (T2HSOMs), which are grids of topologically organised memory nodes with dedicated sensitivity to time-bound sequences of letters. These maps can provide a rigorous and testable conceptual framework within which to provide a comprehensive, multi-task protocol for testing the perform-ance of Hebbian self-organising memories, and a comprehensive picture of the complex dynamics between lexical processing and the acquisition of morphological structure. |
| File Format | |
| Access Restriction | Open |
| Subject Keyword | Hebbian Self-organizing Memory Lexical Representation Hebbian Self-organising Memory Multi-task Protocol Testable Conceptual Framework Present Contribution Long-term Memory Lexical Processing Complex Dynamic Time-bound Sequence Biologically-inspired Computational Model Novel Computational Architecture Organised Memory Node Lexical Competence Morphological Structure Comprehensive Picture Multi-task Evaluation Protocol Lexical Storage Topological Temporal Hebbian Som Mental Lexicon Dedicated Sensitivity |
| Content Type | Text |
