Learn More
Recent years have produced great advances in training large, deep neural networks (DNNs), including notable successes in training convolu-tional neural networks (convnets) to recognize natural images. However, our understanding of how these models work, especially what computations they perform at intermediate layers, has lagged behind. Progress in the(More)
Boosted decision trees are among the most popular learning techniques in use today. While exhibiting fast speeds at test time, relatively slow training renders them impractical for applications with real-time learning requirements. We propose a principled approach to overcome this drawback. We prove a bound on the error of a decision stump given its(More)
Group-Lasso estimators, useful in many applications, suffer from lack of meaningful variance estimates for regression coefficients. To overcome such problems, we propose a full Bayesian treatment of the Group-Lasso, extending the standard Bayesian Lasso, using hierarchical expansion. The method is then applied to Poisson models for contingency tables using(More)
We present a probabilistic model for clustering of objects represented via pairwise dissimilari-ties. We propose that even if an underlying vec-torial representation exists, it is better to work directly with the dissimilarity matrix hence avoiding unnecessary bias and variance caused by em-beddings. By using a Dirichlet process prior we are not obliged to(More)
The detection of multiple objects in noisy images without an explicit model is one of the most challenging tasks in computer vision. In this paper we propose a novel object detection algorithm, termed inter-active tree ensemble (ITE), which can be applied in an off-the-shelf manner to a large variety of tasks.
In the field of neuroanatomy, automatic segmentation of electron microscopy images is becoming one of the main limiting factors in getting new insights into the functional structure of the brain. We propose a novel framework for the segmentation of thin elongated structures like membranes in a neuroanatomy setting. The probability output of a random forest(More)
The histological assessment of human tissue has emerged as the key challenge for detection and treatment of cancer. A plethora of different data sources ranging from tissue microarray data to gene expression, proteomics or metabolomics data provide a detailed overview of the health status of a patient. Medical doctors need to assess these information(More)
Renal cell carcinoma (RCC) can be diagnosed by histological tissue analysis where exact counts of cancerous cell nuclei are required. We propose a completely automated image analysis pipeline to predict the survival of RCC patients based on the analysis of immunohistochemical staining of MIB-1 on tissue microarrays. A random forest classifier detects cell(More)
In neuroanatomy, automatic geometry extraction of neurons from electron microscopy images is becoming one of the main limiting factors in getting new insights into the functional structure of the brain. We propose a novel framework for tracing neuronal processes over serial sections for 3d reconstructions. The automatic processing pipeline combines the(More)
This paper presents a model based approach to autonomous dexterous manipulation, developed as part of the DARPA Autonomous Robotic Manipulation (ARM) program. The developed autonomy system uses robot, object, and environment models to identify and localize objects, and well as plan and execute required manipulation tasks. Deliberate interaction with objects(More)