In this paper, we adopt a supervised machine learning approach to recognize six basic emotions (anger, disgust, fear, happiness, sadness and surprise) using a heterogeneous emotion...
Real-world, multiple-typed objects are often interconnected, forming heterogeneous information networks. A major challenge for link-based clustering in such networks is its potent...
We propose a new loss function for discriminative learning of Markov random fields, which is an intermediate loss function between the sequential loss and the pointwise loss. We s...
An object-oriented neural network simulator kernel is presented. It is based on a general mathematical model for arbitrary feedforward nets. We propose a C++ implementation of thi...
I develop technological tools to help communities of children creatively solve problems as they program computers. The Hook-ups project introduces computational tools that support...