Spatial-temporal reasoning is a challenging task in Artificial Intelligence (AI) due to its demanding but unique nature: a theoretic requirement on representing and reasoning based on spatial-temporal knowledge in mind, and an applied requirement on a high-level cognitive system capable of navigating and acting in space and time. Recent works have focused on an abstract reasoning task of this kind -- Raven's Progressive Matrices (RPM). Despite the encouraging progress on RPM that achieves human-level performance in terms of accuracy, modern approaches have neither a treatment of human-like reasoning on generalization, nor a potential to generate answers. To fill in this gap, we propose a neuro-symbolic Probabilistic Abduction and Execution (PrAE) learner; central to the PrAE learner is the process of probabilistic abduction and execution on a probabilistic scene representation, akin to the mental manipulation of objects. Specifically, we disentangle perception and reasoning from a monolithic model. The neural visual perception frontend predicts objects' attributes, later aggregated by a scene inference engine to produce a probabilistic scene representation. In the symbolic logical reasoning backend, the PrAE learner uses the representation to abduce the hidden rules. An answer is predicted by executing the rules on the probabilistic representation. The entire system is trained end-to-end in an analysis-by-synthesis manner without any visual attribute annotations. Extensive experiments demonstrate that the PrAE learner improves cross-configuration generalization and is capable of rendering an answer, in contrast to prior works that merely make a categorical choice from candidates.

We introduce the problem of robust subgroup discovery, i.e., finding a set of interpretable descriptions of subsets that 1) stand out with respect to one or more target attributes, 2) are statistically robust, and 3) non-redundant. Many attempts have been made to mine either locally robust subgroups or to tackle the pattern explosion, but we are the first to address both challenges at the same time from a global perspective. First, we formulate a broad model class of subgroup lists, i.e., ordered sets of subgroups, for univariate and multivariate targets that can consist of nominal or numeric variables. This novel model class allows us to formalize the problem of optimal robust subgroup discovery using the Minimum Description Length (MDL) principle, where we resort to optimal Normalized Maximum Likelihood and Bayesian encodings for nominal and numeric targets, respectively. Notably, we show that our problem definition is equal to mining the top-1 subgroup with an information-theoretic quality measure plus a penalty for complexity. Second, as finding optimal subgroup lists is NP-hard, we propose RSD, a greedy heuristic that finds good subgroup lists and guarantees that the most significant subgroup found according to the MDL criterion is added in each iteration, which is shown to be equivalent to a Bayesian one-sample proportions, multinomial, or t-test between the subgroup and dataset marginal target distributions plus a multiple hypothesis testing penalty. We empirically show on 54 datasets that RSD outperforms previous subgroup set discovery methods in terms of quality and subgroup list size.

The unification of statistical (data-driven) and symbolic (knowledge-driven) methods is widely recognised as one of the key challenges of modern AI. Recent years have seen large number of publications on such hybrid neuro-symbolic AI systems. That rapidly growing literature is highly diverse and mostly empirical, and is lacking a unifying view of the large variety of these hybrid systems. In this paper we analyse a large body of recent literature and we propose a set of modular design patterns for such hybrid, neuro-symbolic systems. We are able to describe the architecture of a very large number of hybrid systems by composing only a small set of elementary patterns as building blocks. The main contributions of this paper are: 1) a taxonomically organised vocabulary to describe both processes and data structures used in hybrid systems; 2) a set of 15+ design patterns for hybrid AI systems, organised in a set of elementary patterns and a set of compositional patterns; 3) an application of these design patterns in two realistic use-cases for hybrid AI systems. Our patterns reveal similarities between systems that were not recognised until now. Finally, our design patterns extend and refine Kautz' earlier attempt at categorising neuro-symbolic architectures.

We will discuss how over the last 30 to 50 years, systems that focused only on data have been handicapped with success focused on narrowly focused tasks, and knowledge has been critical in developing smarter, intelligent, more effective systems. We will draw a parallel with the role of knowledge and experience in human intelligence based on cognitive science. And we will end with the recent interest in neuro-symbolic or hybrid AI systems in which knowledge is the critical enabler for combining data-intensive statistical AI systems with symbolic AI systems which results in more capable AI systems that support more human-like intelligence.

Actionable Cognitive Twins are the next generation Digital Twins enhanced with cognitive capabilities through a knowledge graph and artificial intelligence models that provide insights and decision-making options to the users. The knowledge graph describes the domain-specific knowledge regarding entities and interrelationships related to a manufacturing setting. It also contains information on possible decision-making options that can assist decision-makers, such as planners or logisticians. In this paper, we propose a knowledge graph modeling approach to construct actionable cognitive twins for capturing specific knowledge related to demand forecasting and production planning in a manufacturing plant. The knowledge graph provides semantic descriptions and contextualization of the production lines and processes, including data identification and simulation or artificial intelligence algorithms and forecasts used to support them. Such semantics provide ground for inferencing, relating different knowledge types: creative, deductive, definitional, and inductive. To develop the knowledge graph models for describing the use case completely, systems thinking approach is proposed to design and verify the ontology, develop a knowledge graph and build an actionable cognitive twin. Finally, we evaluate our approach in two use cases developed for a European original equipment manufacturer related to the automotive industry as part of the European Horizon 2020 project FACTLOG.

Machine learning (ML) is successful in achieving human-level performance in various fields. However, it lacks the ability to explain an outcome due to its black-box nature. While existing explainable ML is promising, almost all of these methods focus on formatting interpretability as an optimization problem. Such a mapping leads to numerous iterations of time-consuming complex computations, which limits their applicability in real-time applications. In this paper, we propose a novel framework for accelerating explainable ML using Tensor Processing Units (TPUs). The proposed framework exploits the synergy between matrix convolution and Fourier transform, and takes full advantage of TPU's natural ability in accelerating matrix computations. Specifically, this paper makes three important contributions. (1) To the best of our knowledge, our proposed work is the first attempt in enabling hardware acceleration of explainable ML using TPUs. (2) Our proposed approach is applicable across a wide variety of ML algorithms, and effective utilization of TPU-based acceleration can lead to real-time outcome interpretation. (3) Extensive experimental results demonstrate that our proposed approach can provide an order-of-magnitude speedup in both classification time (25x on average) and interpretation time (13x on average) compared to state-of-the-art techniques.

In recent years, the world has witnessed various primitives pertaining to the complexity of human behavior. Identifying an event in the presence of insufficient, incomplete, or tentative premises along with the constraints on resources such as time, data and memory is a vital aspect of an intelligent system. Data explosion presents one of the most challenging research issues for intelligent systems; to optimally represent and store this heterogeneous and voluminous data semantically to provide human behavior. There is a requirement of intelligent but personalized human behavior subject to constraints on resources and priority of the user. Knowledge, when represented in the form of an ontology, procures an intelligent response to a query posed by users; but it does not offer content in accordance with the user context. To this aim, we propose a model to quantify the user context and provide semantic contextual reasoning. A diagnostic belief algorithm (DBA) is also presented that identifies a given event and also computes the confidence of the decision as a function of available resources, premises, exceptions, and desired specificity. We conduct an empirical study in the domain of day-to-day routine queries and the experimental results show that the answer to queries and also its confidence varies with user context.

Machine Learning (ML) seems to be one of the most promising solution to automate partially or completely some of the complex tasks currently realized by humans, such as driving vehicles, recognizing voice, etc. It is also an opportunity to implement and embed new capabilities out of the reach of classical implementation techniques. However, ML techniques introduce new potential risks. Therefore, they have only been applied in systems where their benefits are considered worth the increase of risk. In practice, ML techniques raise multiple challenges that could prevent their use in systems submitted to certification constraints. But what are the actual challenges? Can they be overcome by selecting appropriate ML techniques, or by adopting new engineering or certification practices? These are some of the questions addressed by the ML Certification 3 Workgroup (WG) set-up by the Institut de Recherche Technologique Saint Exup\'ery de Toulouse (IRT), as part of the DEEL Project.

It's widely presumed that artificial intelligence (AI) will play a dominant role in future wars. However, the way the future unfolds might be nothing like that. AI developments increasingly led by machine learning-enabled technologies, seem to be going in another direction. AI is a fairly plastic term. Its meaning has shifted over time, reflecting changes in both our understanding of what intelligence is and in the technology available to mimic this.

This paper presents a quick learning mechanism for intelligent fault diagnosis of rotating machines operating under changeable working conditions. Since real case machines in industries run under different operating conditions, the deep learning model trained for a laboratory case machine fails to perform well for the fault diagnosis using recorded data from real case machines. It poses the need of training a new diagnostic model for the fault diagnosis of the real case machine under every new working condition. Therefore, there is a need for a mechanism that can quickly transform the existing diagnostic model for machines operating under different conditions. we propose a quick learning method with Net2Net transformation followed by a fine-tuning method to cancel/minimize the maximum mean discrepancy of the new data to the previous one. This transformation enables us to create a new network with any architecture almost ready to be used for the new dataset. The effectiveness of the proposed fault diagnosis method has been demonstrated on the CWRU dataset, IMS bearing dataset, and Paderborn university dataset. We have shown that the diagnostic model trained for CWRU data at zero load can be used to quickly train another diagnostic model for the CWRU data at different loads and also for the IMS dataset. Using the dataset provided by Paderborn university, it has been validated that the diagnostic model trained on artificially damaged fault dataset can be used for quickly training another model for real damage dataset.