Deductive rules in holographic reduced representation
نویسندگان
چکیده
منابع مشابه
Deductive rules in holographic reduced representation
Holographic reduced representation is based on a suitable distributive coding of structured information in conceptual vectors, which elements satisfy normal distribution N(0,1/n). Existing applications of this approach concern various models of associative memory that exploit a simple algebraic operation of scalar product of distributed representations to measure an overlap between two structur...
متن کاملGeometric Analogue of Holographic Reduced Representation
Holographic reduced representations (HRR) are based on superpositions of convolution-bound ntuples, but the n-tuples cannot be regarded as vectors since the formalism is basis dependent. This is why HRR cannot be associated with geometric structures. Replacing convolutions by geometric products one arrives at reduced representations analogous to HRR but interpretable in terms of geometry. Varia...
متن کاملModels, Rules, and Deductive Reasoning
We formulate a simple theory of deductive reasoning based on mental models. One prediction of the theory is experimentally tested and found to be incorrect. The bearing of our results on contemporary theories of mental models is discussed. We then consider a potential objection to current rule-theories of deduction. Such theories picture deductive reasoning as the successive application of infe...
متن کاملHolographic reduced representations
Associative memories are conventionally used to represent data with very simple structure: sets of pairs of vectors. This paper describes a method for representing more complex compositional structure in distributed representations. The method uses circular convolution to associate items, which are represented by vectors. Arbitrary variable bindings, short sequences of various lengths, simple f...
متن کاملEncoding Sequential Information in Semantic Space Models: Comparing Holographic Reduced Representation and Random Permutation
Circular convolution and random permutation have each been proposed as neurally plausible binding operators capable of encoding sequential information in semantic memory. We perform several controlled comparisons of circular convolution and random permutation as means of encoding paired associates as well as encoding sequential information. Random permutations outperformed convolution with resp...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Neurocomputing
سال: 2006
ISSN: 0925-2312
DOI: 10.1016/j.neucom.2005.09.011