Random Ferns Method / Classifier google
Random ferns is a machine learning algorithm proposed by Ozuysal, Fua, and Lepetit (2007) for matching the same elements between two images of the same scene, allowing one to recognize certain objects or trace them on videos. The original motivation behind this method was to create a simple and e cient algorithm by extending the naive Bayes classifier; still the authors acknowledged its strong connection to decision tree ensembles like the random forest algorithm (Breiman 2001). Since introduction, random ferns have been applied in numerous computer vision applications, like image recognition (Bosch, Zisserman, and Munoz 2007), action recognition (Oshin, Gilbert, Illingworth, and Bowden 2009) or augmented reality (Wagner, Reitmayr, Mulloni, Drummond, and Schmalstieg 2010). However, it has not gathered attention outside this eld; thus, this work aims to bring this algorithm to a much wider spectrum of applications. In order to do that, I propose a generalized version of the algorithm, implemented in the R (R Core Team 2014) package rFerns (Kursa 2014) which is available from the Comprehensive R Archive Network (CRAN) at http://…/package=rFerns.

On-Disk Data Processing (ODDP) google
In this paper, we present a survey of ‘on-disk’ data processing (ODDP). ODDP, which is a form of near-data processing, refers to the computing arrangement where the secondary storage drives have the data processing capability. Proposed ODDP schemes vary widely in terms of the data processing capability, target applications, architecture and the kind of storage drive employed. Some ODDP schemes provide only a specific but heavily used operation like sort whereas some provide a full range of operations. Recently, with the advent of Solid State Drives, powerful and extensive ODDP solutions have been proposed. In this paper, we present a thorough review of architectures developed for different on-disk processing approaches along with current and future challenges and also identify the future directions which ODDP can take. …

Convexified Convolutional Neural Networks (CCNN) google
We describe the class of convexified convolutional neural networks (CCNNs), which capture the parameter sharing of convolutional neural networks in a convex manner. By representing the nonlinear convolutional filters as vectors in a reproducing kernel Hilbert space, the CNN parameters can be represented as a low-rank matrix, which can be relaxed to obtain a convex optimization problem. For learning two-layer convolutional neural networks, we prove that the generalization error obtained by a convexified CNN converges to that of the best possible CNN. For learning deeper networks, we train CCNNs in a layer-wise manner. Empirically, CCNNs achieve performance competitive with CNNs trained by backpropagation, SVMs, fully-connected neural networks, stacked denoising auto-encoders, and other baseline methods. …