This paper proposes novel hierarchical self-organizing associative memory architecture for machine learning. This memory architecture is characterized with sparse and local interco...
The goal of emotion classification is to estimate an emotion label, given representative data and discriminative features. Humans are very good at deriving high-level representat...
We present a novel self-stabilizing version of Mazurkiewicz enumeration algorithm [1]. The initial version is based on local rules to enumerate nodes on an anonymous network. [2] p...
We present a case study to demonstrate the possibility of discovering complex and interesting latent structures using hierarchical latent class (HLC) models. A similar effort was m...
Categories in multi-class data are often part of an underlying semantic taxonomy. Recent work in object classification has found interesting ways to use this taxonomy structure t...