Publications (4)
The .serva Standard: One Primitive for All AI Cost Reduced, Barriers Removed
Rachel St. Clair, John Austin Cook, Peter Sutor +2
Artificial Intelligence (AI) infrastructure faces two compounding crises. Compute payload - the unsustainable energy and capital costs of training and inference - threatens to outp…
Representing Sets as Summed Semantic Vectors
Douglas Summers-Stay, Peter Sutor, Dandan Li
Representing meaning in the form of high dimensional vectors is a common and powerful tool in biologically inspired architectures. While the meaning of a set of concepts can be sum…
Gluing Neural Networks Symbolically Through Hyperdimensional Computing
Peter Sutor, Dehao Yuan, Douglas Summers-Stay +2
Hyperdimensional Computing affords simple, yet powerful operations to create long Hyperdimensional Vectors (hypervectors) that can efficiently encode information, be used for learn…
A Computational Theory for Life-Long Learning of Semantics
Peter Sutor, Douglas Summers-Stay, Yiannis Aloimonos
Semantic vectors are learned from data to express semantic relationships between elements of information, for the purpose of solving and informing downstream tasks. Other models ex…