Learning Hierarchical Spectral Representations of Human Speech with the Information Dynamics of Thinking

Research output: Unpublished contribution to conferenceUnpublished abstract

21 Downloads (Pure)

Abstract

The Information Dynamics of Thinking (IDyOT) is a cognitive architecture based around the principle that the human mind seeks to represent data in the most information-efficient way possible. By blending conceptual spaces theory and information theory, and making a minimal set of assumptions, IDyOT specifies three main processes -- segmentation, categorization, and abstraction -- that hierarchically generate spectral representations of perceptual data in an information-efficient manner.

This thesis is primarily an explication of the propositions and claims introduced in IDyOT by applying the mathematical formalisms of Hilbert spaces and the Fourier transform as implementations of the aforementioned theoretical processes. After deriving the necessary mathematics in order to implement the architecture, an implemented system is empirically tested on a corpus of human speech, where we expected to see the emergence of distinct semantic categories corresponding to human speech sound syllables.
Original languageEnglish
Publication statusPublished - 30 Nov 2019
EventBNAIC 2019 - Brussels, Belgium
Duration: 7 Nov 20198 Nov 2019

Conference

ConferenceBNAIC 2019
Country/TerritoryBelgium
CityBrussels
Period7/11/198/11/19

Fingerprint

Dive into the research topics of 'Learning Hierarchical Spectral Representations of Human Speech with the Information Dynamics of Thinking'. Together they form a unique fingerprint.

Cite this