Batch Normalization is quite effective at accelerating and improving the training of deep models. However, its effectiveness diminishes when the training minibatches are small, or do not consist of independent samples. We hypothesize that this is due to the dependence of model layer inputs on all the examples in the minibatch, and different activations being produced between training and infere...

These days, ongoing research towards interactivity to break the persevering batch processing paradigm in grid computing can be seen. Batch processing means: submit a job to a queue, process it and, only when the job is finished, analyse the results. By extending grid middleware through an interactive jobmanager, a novel approach to support applications which require interactive connections is p...

In this paper, we consider an integrated scheduling problem of production and distribution for manufacturers. In the production part, the batch-processing machines have fixed capacity and the jobs have arbitrary sizes and processing times. Jobs in a batch can be processed together, provided that the total size of the jobs in the batch does not exceed the machine capacity. The processing time of...

Article history: Received 9 November 2007 Received in revised form 17 March 2008 Accepted 3 April 2008 Available online 6 April 2008

A resource typically executes a particular activity on a series of cases. When a resource performs an activity on several cases simultaneously, (quasi-) sequentially or concurrently, this is referred to as batch processing. Given its influence on process performance, batch processing needs to be taken into account when modeling business processes for performance evaluation purposes. This paper ...

Data warehouses are a challenging field of application for data mining tasks such as clustering. Usually, updates are collected and applied to the data warehouse periodically in a batch mode. As a consequence, all mined patterns discovered in the data warehouse (e.g. clustering structures) have to be updated as well. In this paper, we present a method for incrementally updating the clustering s...

With the growing need of processing “big data” in real time, modern streaming processing systems should be able to operate at the cloud scale. This imposes challenges to building large scale stream processing systems. First, processing tasks should be efficiently distributed to worker nodes with small overhead. Second, streaming data processing should be highly available, despite that failures ...

The overhead of processing fine-grain tasks on a grid induces the need for batch processing or task group deployment in order to minimise overall application turnaround time. When deciding the granularity of a batch, the processing requirements of each task should be considered as well as the utilisation constraints of the interconnecting network and the designated resources. However, the dynam...

Differential privacy is a promising privacy-preserving paradigm for statistical query processing over sensitive data. It works by injecting random noise into each query result, such that it is provably hard for the adversary to infer the presence or absence of any individual record from the published noisy results. The main objective in differentially private query processing is to maximize the...

In this paper, we discuss the “batch processing” problem, where there are multiple jobs to be processed in flow shops. These jobs can however be formed into batches and the number of jobs in a batch is limited by the capacity of the processing machines to accommodate the jobs. The processing time required by a batch in a machine is determined by the greatest processing time of the jobs included...