Classification of data that arise as signals or images often requires a standardization step so that information extracted from biologically equivalent signals can be quantified for comparison across classes. Differences in global trend, total energy, high-frequency noise and/or local background can arise from variabilities due to instrumentation or conditions during data collection. This artic...

We propose a unified framework for neural net normalization, regularization and optimization, which includes Path-SGD and Batch-Normalization and interpolates between them across two different dimensions. Through this framework we investigate issue of invariance of the optimization, data dependence and the connection with natural gradients.

Normalization of expression levels applied to microarray data can help in reducing measurement error. Different methods, including cyclic loess, quantile normalization and median or mean normalization, have been utilized to normalize microarray data. Although there is considerable literature regarding normalization techniques for mRNA microarray data, there are no publications comparing normali...

A preliminary analysis of low-energy e+e− collision data produced via initial state radiation (ISR) has been performed using 22f b−1 of BaBar data. The selection of data samples corresponding to the μ+μ−, π+π−, K+K−, pp̄, K+K−π0, 3π , 4π , 5π , 6π , 7π final states accompanied by the emitted ISR hard photon has been demonstrated. The invariant mass of the hadronic final state defines the effecti...

We present a method to detect intensity changes in longitudinal volumetric MRI data from patients with multiple sclerosis (MS). Preprocessing includes spatial and intensity normalization. The intrasubject intensity normalization is achieved using a polynomial least trimmed squares method to match the histograms of all images in the series. Viewing the detection of disease activity in MRI as a c...

The e cient usage of workstations clusters depends rst of all on the distribution of the workload The following paper introduces a method to obtain e cient load balancing for data parallel applications through dynamic data assignment and a simple priority mechanism on a heterogeneous cluster of workstations assuming no prior knowledge about the workload This model improves the performance of lo...

This paper presents an automated method for normalizing measurable properties of tracked objects that lie primarily on a ground plane in far-field tracking scenarios (e.g., video surveillance). The normalization of properties such as sizes, lengths, and heights is accomplished automatically and reliably without assumptions on the type of objects or camera geometry. This normalization enables co...

This paper is concerned with the foundations of Inductive Data Type Systems, an extension of pure type systems by inductive data types. IDTS generalize (inductive) types equipped with primitive recursion of higher-type, by providing de nitions of functions by pattern matching of a form which is general enough to capture recursor de nitions for strictly positive inductive types. IDTS also genera...

Motivations In recent years, RNA sequencing (RNA-seq) has rapidly become the method of choice for measuring and comparing gene transcription levels. Despite its wide application, it is now clear that this methodology is not free from biases and that a careful normalization procedure is the basis for a correct data interpretation. The most common normalization techniques account for: library siz...