When obtaining labels is expensive, the requirement of a large labeled training data set for deep learning can be mitigated by active learning. Active learning refers to the development of algorithms to judiciously pick limited subsets of unlabeled samples that can be sent for labeling by an oracle. We propose an intuitive active learning technique that, in addition to the task neural network (e.g., for classification), uses an auxiliary self-supervised neural network that assesses the utility of an unlabeled sample for inclusion in the labeled set. Our core idea is that the difficulty of the auxiliary network trained on labeled samples to solve a self-supervision task on an unlabeled sample represents the utility of obtaining the label of that unlabeled sample. Specifically, we assume that an unlabeled image on which the precision of predicting a random applied geometric transform is low must be out of the distribution represented by the current set of labeled images. These images will therefore maximize the relative information gain when labeled by the oracle. We also demonstrate that augmenting the auxiliary network with task specific training further improves the results. We demonstrate strong performance on a range of widely used datasets and establish a new state of the art for active learning. We also make our code publicly available to encourage further research.
Association rules are the main technique for data mining. Apriori algorithm is a classical algorithm of association rule mining. Lots of algorithms for mining association rules and their mutations are proposed on basis of Apriori algorithm, but traditional algorithms are not efficient. For the two bottlenecks of frequent itemsets mining: the large multitude of candidate 2itemsets, the poor efficiency of counting their support. Proposed algorithm reduces one redundant pruning operations of
Today's businesses need support when making decisions. Business intelligence (BI) helps businesses to make decisions based on good pre-analysis and documented data, and enables information to be presented when and where the decisions need to be made. Real time business intelligence (RTBI) presents numbers in real time, providing the decision makers at the operational and tactical layers with data as fresh as it can be. By having accurate, fresher and a bigger amount of data, businesses will be able to make decisions in a faster pace, and eliminate tedious complexity of the decisionmaking process. The objective of this research is to show that a real time business intelligence solution would be beneficial for supporting the operational and tactical layers of decision-making within an organization. By implementing an RTBI solution, it would provide the decision-maker with fresh and reliant data to base the decisions on. Visualization of the current decision processes showed that by adding a real time business intelligence solution it would help eliminate the use of intuition, as there would be more data available and the decisions can be made where the work is performed. The aim of this research is to contribute by visualizing how a real time business intelligence solution can shorten a complex decision process by giving the correct information to the right people. Organizations need to address potential challenges as part of a pre-project of a real time business intelligence implementation.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.