The just-in-time production philosophy has led to a growing interest in scheduling problems considering both earliness and tardiness penalties. Most publications considering these so-called non-regular objective functions are devoted to single machine problems. In the case of multi-machine problems, there are some papers dealing with parallel machine problems. However, for multi-operation sched...

Current MT systems, whatever translation method they at present employ, do not reach an optimum output on free text. Our hypothesis for the experiment reported in this paper is that if an MT environment can use the best results from a variety of MT systems working simultaneously on the same text, the overallquality will improve. Using this novel approach to MT in the latest version of the Pangl...

Privacy preserving multi-party machine learning approaches enable multiple parties to train a machine learning model from aggregate data while ensuring the privacy of their individual datasets is preserved. In this paper, we propose a privacy preserving multi-party machine learning approach based on homomorphic encryption where the machine learning algorithm of choice is deep neural networks. W...

The idea of Hopfield network is based on the king spin glass model in which each spin has only two possible states: up and down. By introducing stochastic factors into this network and performing a simulated annealing process on it, it becomes a Boltzmann machine which can escape from local minimum states to achieve the global minimum. This paper generalizes the above ideas to multi-value case ...

Ensemble machine learning models often surpass single models in classification accuracy at the expense of higher computational requirements during training and execution. In this paper we present a novel ensemble algorithm called Multi-K which uses unsupervised clustering as a form of dataset preprocessing to create component models that lead to effective and efficient ensembles. We also presen...

Recent efforts aimed at improving the scalability of the Java platform have focused primarily on the safe collocation of multiple applications in the virtual machine. This is often beneficial for various performance metrics, but ultimately leads to a singleuser multitasking environment. The lack of multi-user capabilities forms a barrier to the scalability of multitasking virtual machines, as i...

We extend multiclass SVM to multiple prototypes per class. For this framework, we give a compact constrained quadratic problem and we suggest an efficient algorithm for its optimization that guarantees a local minimum of the objective function. An annealed process is also proposed that helps to escape from local minima. Finally, we report experiments where the performance obtained using linear ...

We consider the scheduling problems arising when several agents, each owning a set of nonpreemptive jobs, compete to perform their respective jobs on one shared processing resource. Each agent wants to minimize a certain cost function, which depends on the completion times of its jobs only. The cost functions we consider in this paper are maximum of regular functions (associated with each job),...