Corpus ID: 7149851

What We Mean When We Say "What's the Dollar of Mexico?": Prototypes and Mapping in Concept Space

@inproceedings{Kanerva2010WhatWM,
  title={What We Mean When We Say "What's the Dollar of Mexico?": Prototypes and Mapping in Concept Space},
  author={Pentti Kanerva},
  booktitle={AAAI Fall Symposium: Quantum Informatics for Cognitive, Social, and Semantic Processes},
  year={2010}
}
  • P. Kanerva
  • Published in
    AAAI Fall Symposium: Quantum…
    1 November 2010
  • Computer Science
We assume that the brain is some kind of a computer and look at operations implied by the figurative use of language. Figurative language is pervasive, bypasses the literal meaning of what is said and is interpreted metaphorically or by analogy. Such an interpretation calls for a mapping in concept space, leading us to speculate about the nature of concept space in terms of readily computable mappings. We find that mappings of the appropriate kind are possible in high-dimensional spaces and… Expand
Connecting Twenty-First Century Connectionism and Wittgenstein
TLDR
It is shown how connectionist networks can extrapolate meaningful patterns to solve problems, providing “ways to go on” without explicit rules, which indicates linguistic plausibility, and Connectionism provides a systematicity and productivity that is more than a mere implementation of a classical approach. Expand
Using Cortically-Inspired Algorithms for Analogical Learning and Reasoning
TLDR
This work considers the neurologically-inspired hypothesis that higher level cognition is built on the same fundamental building blocks as low-level perception, and presents a system that represents relational structures as feature bags, using algorithms inspired by the sensory cortex to automatically create an ontology of relational structures. Expand
Computing with 10,000-bit words
  • P. Kanerva
  • Computer Science
  • 2014 52nd Annual Allerton Conference on Communication, Control, and Computing (Allerton)
  • 2014
TLDR
The paper describes a 10,000bit architecture that resembles von Neumann's and is suited for statistical learning from data and is used in cognitive modeling and natural-language processing where it is referred to by names such as Holographic Reduce Representation, Vector Symbolic Architecture, Random Indexing, Semantic Indexing and Semantic Pointer Architecture. Expand
Who is the cowboy in Washington?: beating google at their own game with neuroscience and cryptography
TLDR
Building on top of the mathematical model of memory called Sparse Distributed Memory, it will be seen how some well-known methods in cryptography can point toward a promising, comprehensive, solution that preserves four crucial properties of human psychology. Expand
Reasoning with vectors: A continuous model for fast robust inference
TLDR
The paper explains the way logical connectives can be used in semantic vector models, and summarizes the development of Predication-based Semantic Indexing, which involves the use of Vector Symbolic Architectures to represent the concepts and relationships from a knowledge base of subject-predicate-object triples. Expand
Variable Binding for Sparse Distributed Representations: Theory and Applications
TLDR
This work shows that variable binding between dense vectors in VSAs is mathematically equivalent to tensor product binding between sparse vectors, an operation which increases dimensionality, and shows that dimensionality-preserving binding for general sparse vectors must include a reduction of the tensor matrix into a single sparse vector. Expand
Embedding of semantic predications
TLDR
This paper develops a novel neural-probabilistic approach to encoding predications, called Embedding of Semantic Predications (ESP), by adapting aspects of the Skipgram with Negative Sampling (SGNS) algorithm to this purpose and compares ESP and PSI across a number of tasks. Expand
Recursive functions in high-dimensional computing with random vectors
TLDR
Recursion construction of mappings and functions in high-dimensional computing with random vectors is demonstrated in a connectionist computing model which provides benefits similar to neural networks, but allows compositional learning. Expand
Implications of Computational Cognitive Models for Information Retrieval
TLDR
The HAM-TMC users view an abstract text and determine from that abstract text that they are not interested in reading the full text. Expand
Exploring Embedding Methods in Binary Hyperdimensional Computing: A Case Study for Motor-Imagery based Brain-Computer Interfaces
Key properties of brain-inspired hyperdimensional (HD) computing make it a prime candidate for energy-efficient and fast learning in biosignal processing. The main challenge is however to formulateExpand
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 26 REFERENCES
Metaphors We Live by
Every linguist dreams of the day when the intricate variety of human language will be a commonplace, widely understood in our own and other cultures; when we can unlock the secrets of human thoughtExpand
The analogical mind : perspectives from cognitive science
Analogy has been the focus of extensive research in cognitive science over the past two decades. Through analogy, novel situations and problems can be understood in terms of familiar ones. Indeed, aExpand
Conceptual Spaces — The Geometry of Thought
nightmare—small changes in the intended semantics of predicates or procedures cause large and usually catastrophic changes in performance. There have been, I think, two responses to this. One is owedExpand
Douglas Hofstadter and the Fluid Analogies Research Group, Fluid Concepts and Creative Analogies: Computer Models of the Fundamental Mechanisms of Thought
  • M. Boden
  • Computer Science, Psychology
  • Minds and Machines
  • 2004
TLDR
Douglas Hofstadter’s computer models are intriguingly different from most others, and focus on an aspect of human thinking often claimed by post-Wittgensteinian philosophers to lie beyond the scope of any possible computational approach: its creative capacity to extend or reconfigure concepts endlessly, as the context changes. Expand
Representing word meaning and order information in a composite holographic lexicon.
TLDR
A computational model that builds a holographic lexicon representing both word meaning and word order from unsupervised experience with natural language demonstrates that a broad range of psychological data can be accounted for directly from the structure of lexical representations learned in this way, without the need for complexity to be built into either the processing mechanisms or the representations. Expand
A Solution to Plato's Problem: The Latent Semantic Analysis Theory of Acquisition, Induction, and Representation of Knowledge.
How do people know as much as they do with as little information as they get? The problem takes many forms; learning vocabulary from text is an especially dramatic and convenient case for research. AExpand
On learning the past-tenses of English verbs: implicit rules or parallel distributed processing
TLDR
It is shown how rule-like behavior can emerge from the interactions among a network of units encoding the root form to past tense mapping, and how details of the acquisition process not captured by the rule account emerge. Expand
Analogical Mapping by Constraint Satisfaction
TLDR
A theory of analogical mapping between source and target analogs based upon interacting structural, semantic, and pragmatic constraints is proposed here and is able to account for empirical findings regarding the impact of consistency and similarity on human processing of analogies. Expand
Hyperdimensional Computing: An Introduction to Computing in Distributed Representation with High-Dimensional Random Vectors
  • P. Kanerva
  • Computer Science
  • Cognitive Computation
  • 2009
TLDR
The thesis of the paper is that hyperdimensional representation has much to offer to students of cognitive science, theoretical neuroscience, computer science and engineering, and mathematics. Expand
Geometry and Meaning
  • D. Widdows
  • Mathematics, Computer Science
  • Computational Linguistics
  • 2006
TLDR
What the "Geometry of Meaning" provides is a much-needed exploration of computational techniques to represent meaning and of the conceptual spaces on which these representations are founded. Expand
...
1
2
3
...