Cats or CAT scans: Transfer learning from natural or medical image source data sets?

Heavy metals in coastal sediments of South Caspian Sea: natural or anthropogenic source?

This paper focuses on heavy metal distribution patterns in sediments of central Guilan (CG) and east Mazandaran (EM) in the south Caspian Sea coasts, north of Iran. Sediment sub-samples were retrieved from core and surficial samples in different environments of marine and coastal lagoons as well as coastal outcrops. Inductively Coupled Plasma Mass Spectrometry and Atomic Emission Spectrometry (...

Learning Local Distortion Visibility From Image Quality Data-sets

Accurate prediction of local distortion visibility thresholds is critical in many image and video processing applications. Existing methods require an accurate modeling of the human visual system, and are derived through pshycophysical experiments with simple, artificial stimuli. These approaches, however, are difficult to generalize to natural images with complex types of distortion. In this p...

MML , inverse learning , and medical data - sets

f/sla from learner perspectives: a social activity or a cognitive process

in the past couple of decades sociocultural theory of sla and its implications in efl contexts have attracted attentions of research circles worldwide and aroused some controversies. firth and wagner (1997) have questioned the principles of the cognitive view which gives importance to mental constructs in favor of sociocultural view which highlights social and contextual constructs. but if soci...

Learning Bayesian network parameters from small data sets: application of Noisy-OR gates

Existing data sets of cases can significantly reduce the knowledge engineering effort required to parameterize Bayesian networks. Unfortunately, when a data set is small, many conditioning cases are represented by too few or no data records and they do not offer sufficient basis for learning conditional probability distributions. We propose a method that uses Noisy-OR gates to reduce the data r...