PhD Proposal: Hyperdimensional Binary Vector Models for Representation, Integration and Learning of Arbitrary Data
Peter Sutor
Abstract
|
|
Bio
Peter Sutor is a doctoral student in computer science. He is interested in hyperdimensional computing and how it can be applied to modern machine learning and AI techniques to create a universal symbolic encoding of information between vastly different learning architectures, thereby integrating them into a more general, life-long learning system. For example, how can we make an AI that understands language, vision, etc., as arbitrary signals and symbolic representations, and continually learn from them? Other research interests include vector symbolic architectures, vector embeddings, neural network based learning, computer vision, and computational linguistics.
This talk is organized by Tom Hurst