In 3D virtual environments (3DVE), we need to know what an object looks like (i.e. geometric information) and what the object is, what are its properties and characteristics and ho...
The eventual goal of a language model is to accurately predict the value of a missing word given its context. We present an approach to word prediction that is based on learning a...
Scarcity and infeasibility of human supervision for large
scale multi-class classification problems necessitates active
learning. Unfortunately, existing active learning methods
...
Prateek Jain (University of Texas at Austin), Ashi...
The content of information security curricula spans a wide array of topics. Because of this variety, a program needs to focus on some particular aspect and provide appropriate dep...
The standard framework of machine learning problems assumes that the available data is independent and identically distributed (i.i.d.). However, in some applications such as image...