Learn More
Algorithms for data-driven learning of domain-specific overcomplete dictionaries are developed to obtain maximum likelihood and maximum a posteriori dictionary estimates based on the use of Bayesian models with concave/Schur-concave (CSC) negative log priors. Such priors are appropriate for obtaining sparse representations of environmental signals within an(More)
We compare machine learning methods applied to a difficult real-world problem: predicting computer hard-drive failure using attributes monitored internally by individual drives. The problem is one of detecting rare events in a time series of noisy and nonparametrically-distributed data. We develop a new algorithm based on the multiple-instance learning(More)
—Improved methods are proposed for disk-drive failure prediction. The SMART (Self Monitoring and Reporting Technology) failure prediction system is currently implemented in disk-drives. Its purpose is to predict the near-term failure of an individual hard disk-drive, and issue a backup warning to prevent data loss. Two experimental tests of SMART show only(More)
— We present a case study of a difficult real-world pattern recognition problem: predicting hard drive failure using attributes monitored internally by individual drives. We compare the performance of support vector machines (SVMs), unsupervised clustering, and non-parametric statistical tests (rank-sum and reverse arrangements). Somewhat surprisingly, the(More)
Yearly tidal datum statistics and tide ranges for the National Oceanic and Atmospheric Administration/National Ocean Service long-term stations in the United States tide gauge network were compiled and used to calculate their trends and statistical significance. At many stations, significant changes in the tide range were found, either in the diurnal tide(More)
Convolutional networks have achieved a great deal of success in high-level vision problems such as object recognition. Here we show that they can also be used as a general method for low-level image processing. As an example of our approach, convolutional networks are trained using gradient learning to solve the problem of restoring noisy or degraded(More)
Information storage reliability and security is addressed by using personal computer disk drives in enterprise-class nearline and archival storage systems. The low cost of these serial ATA (SATA) PC drives is a tradeoff against drive reliability design and demonstration test levels, which are higher in the more expensive SCSI and Fibre Channel drives. This(More)
Unprecedented numbers of children experience parental incarceration worldwide. Families and children of prisoners can experience multiple difficulties after parental incarceration, including traumatic separation, loneliness, stigma, confused explanations to children, unstable childcare arrangements, strained parenting, reduced income, and home, school, and(More)
Qualitative studies suggest that children react to parental imprisonment by developing internalizing as well as externalizing behaviors. However, no previous study has examined the effects of parental imprisonment on children's internalizing problems using standardized instruments, appropriate comparison groups, and long-term follow-up. Using prospective(More)
Many image segmentation algorithms first generate an affinity graph and then partition it. We present a machine learning approach to computing an affinity graph using a convolutional network (CN) trained using ground truth provided by human experts. The CN affinity graph can be paired with any standard partitioning algorithm and improves segmentation(More)