Cody Kommers

  • Citations Per Year
Learn More
We present a distributed vector representation based on a simplification of the BEAGLE system, designed in the context of the Sigma cognitive architecture. Our method does not require gradient-based training of neural networks, matrix decompositions as with LSA, or convolutions as with BEAGLE. All that is involved is a sum of random vectors and their(More)
Imagination enables us not only to transcend reality but also to learn about it. In the context of reinforcement learning, an agent can rationally update its value estimates by simulating an internal model of the environment, provided that the model is accurate. In a series of sequential decision-making experiments, we investigated the impact of imaginative(More)
Previous computational models of jazz improvisation typically employ algorithms designed to “think” like an improvising jazz musician, each offering distinct advantages and disadvantages. Creating a model that successfully produces jazz improvisation would (1) offer insights into a unique cognitive expertise, (2) elucidate more general creative processes(More)
We demonstrate that distributed vector representations are capable of hierarchical reasoning by summing sets of vectors representing hyponyms (subordinate concepts) to yield a vector that resembles the associated hypernym (superordinate concept). These distributed vector representations constitute a potentially neurally plausible model while demonstrating a(More)
Abstract: Although music exists in every observed culture, ethnomusicologists suggest that music is not the “universal language,” because of the tremendous variation between music of different cultures. However, evidences from mathematics, psychoacoustics, neurobiology, cognitive science, and anthropology suggest an innate inclination of human beings toward(More)
  • 1