In this paper, we present a modified Xception architecture, the NEXcepTion network. Our network has significantly better performance than the original Xception, achieving top-1 accuracy of 81.5% on the ImageNet validation dataset (an improvement of 2.5%) as well as a 28% higher throughput. Another variant of our model, NEXcepTion-TP, reaches 81.8% top-1 accuracy, similar to ConvNeXt (82.1%), while having a 27% higher throughput. Our model is the result of applying improved training procedures and new design decisions combined with an application of Neural Architecture Search (NAS) on a smaller dataset. These findings call for revisiting older architectures and reassessing their potential when combined with the latest enhancements.

Kriging or Gaussian Process Regression is applied in many fields as a non-linear regression model as well as a surrogate model in the field of evolutionary computation. However, the computational and space complexity of Kriging, that is cubic and quadratic in the number of data points respectively, becomes a major bottleneck with more and more data available nowadays. In this paper, we propose a general methodology for the complexity reduction, called cluster Kriging, where the whole data set is partitioned into smaller clusters and multiple Kriging models are built on top of them. In addition, four Kriging approximation algorithms are proposed as candidate algorithms within the new framework. Each of these algorithms can be applied to much larger data sets while maintaining the advantages and power of Kriging. The proposed algorithms are explained in detail and compared empirically against a broad set of existing state-of-the-art Kriging approximation methods on a well-defined testing framework. According to the empirical study, the proposed algorithms consistently outperform the existing algorithms. Moreover, some practical suggestions are provided for using the proposed algorithms.

Recommender systems are increasingly used for personalised navigation through large amounts of information, especially in the e-commerce domain for product purchase advice. Whilst much research effort is spent on developing recommenders further, there is little to no effort spent on analysing the impact of them - neither on the supply (company) nor demand (consumer) side. In this paper, we investigate the diversity impact of a movie recommender. We define diversity for different parts of the domain and measure it in different ways. The novelty of our work is the usage of real rating data (from Netflix) and a recommender system for investigating the (hypothetical) effects of various configurations of the system and users' choice models.We consider a number of different scenarios (which differ in the agent's choice model), run very extensive simulations, analyse various measurements regarding experimental validation and diversity, and report on selected findings. The choice models are an essential part of our work, since these can be influenced by the owner of the recommender once deployed.

We propose a gossip-based distributed algorithm for Gaussian mixture learning, Newscast EM. The algorithm operates on network topologies where each node observes a local quantity and can communicate with other nodes in an arbitrary point-to-point fashion. The main difference between Newscast EM and the standard EM algorithm is that the M-step in our case is implemented in a decentralized manner: (random) pairs of nodes repeatedly exchange their local parameter estimates and combine themby (weighted) averaging. We provide theoretical evidence and demonstrate experimentally that, under this protocol, nodes converge exponentially fastto the correct estimates in each M-step of the EM algorithm.