Various logit-adjusted parameterizations of the cross-entropy (CE) loss have been proposed as alternatives to weighted CE for training large models on label-imbalanced data far beyond the zero train error regime. The driving force behind those designs has been the theory of implicit bias, which for linear(ized) models, explains why they successfully induce bias on the optimization path towards solutions that favor minorities. Aiming to extend this theory to non-linear models, we investigate the implicit geometry of classifiers and embeddings that are learned by different CE parameterizations. Our main result characterizes the global minimizers of a non-convex cost-sensitive SVM classifier for the unconstrained features model, which serves as an abstraction of deep nets. We derive closed-form formulas for the angles and norms of classifiers and embeddings as a function of the number of classes, the imbalance and the minority ratios, and the loss hyperparameters. Using these, we show that logit-adjusted parameterizations can be appropriately tuned to learn symmetric geometries irrespective of the imbalance ratio. We complement our analysis with experiments and an empirical study of convergence accuracy in deep-nets.

Humans learn from the occurrence of events in a different place and time to predict similar trajectories of events. We define Loosely Decoupled Timeseries (LDT) phenomena as two or more events that could happen in different places and across different timelines but share similarities in the nature of the event and the properties of the location. In this work we improve on the use of Recurring Neural Networks (RNN), in particular Long Short-Term Memory (LSTM) networks, to enable AI solutions that generate better timeseries predictions for LDT. We use similarity measures between timeseries based on the trends and introduce embeddings representing those trends. The embeddings represent properties of the event which, coupled with the LSTM structure, can be clustered to identify similar temporally unaligned events. In this paper, we explore methods of seeding a multivariate LSTM from time-invariant data related to the geophysical and demographic phenomena being modeled by the LSTM. We apply these methods on the timeseries data derived from the COVID-19 detected infection and death cases. We use publicly available socio-economic data to seed the LSTM models, creating embeddings, to determine whether such seeding improves case predictions. The embeddings produced by these LSTMs are clustered to identify best-matching candidates for forecasting an evolving timeseries. Applying this method, we show an improvement in 10-day moving average predictions of disease propagation at the US County level.

The Local Digital Twins (LDT) Technology Workshop will bring together technology providers, Research and Technology Organisations, city Chief Technology Officers and other interested players. The aim of the workshop is to raise awareness of digital technology providers and related organisations about the European Union approach regarding Local Digital Twins and discuss how to build European capacity to this end.

With the development of Internet of Things (IoT), IoT intelligence becomes emerging technology. "Curse of Dimensionality" is the barrier of data fusion in edge devices for the success of IoT intelligence. A Linguistic Attribute Hierarchy (LAH), embedded with Linguistic Decision Trees (LDTs), can represent a new attribute deep learning. In contrast to the conventional deep learning, an LAH could overcome the shortcoming of missing interpretation by providing transparent information propagation through the rules, produced by LDTs in the LAH. Similar to the conventional deep learning, the computing complexity of optimising LAHs blocks the applications of LAHs. In this paper, we propose a heuristic approach to constructing an LAH, embedded with LDTs for decision making or classification by utilising the distance correlations between attributes and between attributes and the goal variable. The set of attributes is divided to some attribute clusters, and then they are heuristically organised to form a linguistic attribute hierarchy. The proposed approach was validated with some benchmark decision making or classification problems from the UCI machine learning repository. The experimental results show that the proposed self-organisation algorithm can construct an effective and efficient linguistic attribute hierarchy. Such a self-organised linguistic attribute hierarchy embedded with LDTs can not only efficiently tackle "curse of dimensionality" in a single LDT for data fusion with massive attributes, but also achieve better or comparable performance on decision making or classification, compared to the single LDT for the problem to be solved. The self-organisation algorithm is much efficient than the Genetic Algorithm in Wrapper for the optimisation of LAHs. This makes it feasible to embed the self-organisation algorithm in edge devices for IoT intelligence.

Propositionalization is the process of summarizing relational data into a tabular (attribute-value) format. The resulting table can next be used by any propositional learner. This approach makes it possible to apply a wide variety of learning methods to relational data. However, the transformation from relational to propositional format is generally not lossless: different relational structures may be mapped onto the same feature vector. At the same time, features may be introduced that are not needed for the learning task at hand. In general, it is hard to define a feature space that contains all and only those features that are needed for the learning task. This paper presents LazyBum, a system that can be considered a lazy version of the recently proposed OneBM method for propositionalization. LazyBum interleaves OneBM's feature construction method with a decision tree learner. This learner both uses and guides the propositionalization process. It indicates when and where to look for new features. This approach is similar to what has elsewhere been called dynamic propositionalization. In an experimental comparison with the original OneBM and with two other recently proposed propositionalization methods (nFOIL and MODL, which respectively perform dynamic and static propositionalization), LazyBum achieves a comparable accuracy with a lower execution time on most of the datasets.