We present a hierarchical generative model for object recognition that is constructed by weakly-supervised learning. A key component is a novel, adaptive patch feature whose width...
In machine learning problems with tens of thousands of features and only dozens or hundreds of independent training examples, dimensionality reduction is essential for good learni...
Abstract Bioinformatic data sources available on the web are multiple and heterogenous. The lack of documentation and the difficulty of interaction with these data banks require us...
Attributes define, classify, or annotate the datum to which they are assigned. However, traditional attribute architectures and cryptosystems are ill-equipped to provide security ...
Matthew Pirretti, Patrick Traynor, Patrick McDanie...
Accurate and less invasive personalized predictive medicine can spare many breast cancer patients from receiving complex surgical biopsies, unnecessary adjuvant treatments and its...
Umer Khan, Hyunjung Shin, Jongpill Choi, Minkoo Ki...