Learn More
Is there a principled way to learn a probabilistic discriminative classifier from an unlabeled data set? We present a framework that simultaneously clusters the data and trains a discriminative classifier. We call it Regularized Information Maxi-mization (RIM). RIM optimizes an intuitive information-theoretic objective function which balances class(More)
Clustering is a fundamental task in many vision applications. To date, most clustering algorithms work in a batch setting and training examples must be gathered in a large group before learning can begin. Here we explore incremental clustering, in which data can arrive continuously. We present a novel incremental model-based clustering algorithm based on(More)
Considering that mycobacterial heat-shock protein 65 (hsp65) gene transfer can elicit a profound antitumoral effect, this study aimed to establish the safety, maximum-tolerated dose (MTD) and preliminary efficacy of DNA-hsp65 immunotherapy in patients with advanced head and neck squamous cell carcinoma (HNSCC). For this purpose, 21 patients with(More)
The aim of this study was to evaluate the effects of different concentrations of ascorbic acid (25, 50, and 100 μg/mL) in supplemented minimum essential medium (MEM+) on the development of equine preantral follicles that were cultured in vitro for 2 or 6 days. The contralateral ovaries (n = 5) from five mares in seasonal anestrus were collected from a local(More)
The objective was to evaluate the efficiency of phosphate-buffered saline (PBS) and Minimum Essential Medium (MEM) during the transport of equine preantral and antral follicles at various temperatures and incubation interval. Equine ovaries (n = 10) from an abattoir were cut into 19 fragments; one was immediately fixed in Bouin's solution (control) and the(More)
1 Abstract Clustering is a fundamental task in many vision applications. To date, most clustering algorithms work in a batch setting and training examples must be gathered in a large group before learning can begin. Here we explore incremental clustering, in which data can arrive continuously. We present a novel incremen-tal model-based clustering algorithm(More)
This article discusses the concept of social representations on health and illness from a social/historical point of view, to provide the means for developing research in the public health care domain. To situate this discussion, the analysis was based on field research health issues, attempting to demarcate a theoretical frame of reference with the help of(More)