A vast array of Deep Learning (DL) approaches have been proven successful in many different learning tasks in recent years. One of the key strength of DL models is their ability to automatically learn a representation of the features composing a data set. Deep Neural Networks (DNNs) represent the foremost and widely spread class of DL models. Broadly speaking, DNNs are sub-symbolic ML approaches that are very good at extracting the useful information contained in large data sets. One of the advantages of DL techniques is that, in general, they do not rely on stringent assumptions on the distribution of the underlying data and on the function to be learned or approximated. This allows them to be applied in many different areas with very good results, without significant changes to the DNNs' structure and training algorithm. However, there are contexts where purely data-driven models are not an ideal fit, for example when scarce data of good quality and very difficult learning tasks. In such situations, a great boost in the performance of neural networks (and ML models in general) can be obtained through the exploitation of domain knowledge, e.g.

Markov decision processes are of major interest in the planning community as well as in the model checking community. But in spite of the similarity in the considered formal models, the development of new techniques and methods happened largely independently in both communities. This work is intended as a beginning to unite the two research branches. We consider goal-reachability analysis as a common basis between both communities. The core of this paper is the translation from Jani, an overarching input language for quantitative model checkers, into the probabilistic planning domain definition language (PPDDL), and vice versa from PPDDL into Jani. These translations allow the creation of an overarching benchmark collection, including existing case studies from the model checking community, as well as benchmarks from the international probabilistic planning competitions (IPPC). We use this benchmark set as a basis for an extensive empirical comparison of various approaches from the model checking community, variants of value iteration, and MDP heuristic search algorithms developed by the AI planning community. On a per benchmark domain basis, techniques from one community can achieve state-ofthe-art performance in benchmarks of the other community. Across all benchmark domains of one community, the performance comparison is however in favor of the solvers and algorithms of that particular community. Reasons are the design of the benchmarks, as well as tool-related limitations. Our translation methods and benchmark collection foster crossfertilization between both communities, pointing out specific opportunities for widening the scope of solvers to different kinds of models, as well as for exchanging and adopting algorithms across communities.

Artificial intelligence (AI) comprises a type of computer science that develops entities, such as software programs, that can intelligently perform tasks or make decisions.1 The development and use of AI in health care is not new; the first ideas that created the foundation of AI were documented in 1956, and automated clinical tools that were developed between the 1970s and 1990s are now in routine use. These tools, such as the automated interpretation of electrocardiograms, may seem simple, but are considered AI. Today, AI is being harnessed to help with "big" problems in medicine -- such as processing and interpreting large amounts of data in research and in clinical settings, including reading imaging or results from broad genetic-testing panels.1 In oncology, AI is not yet being used broadly, but its use is being studied in several areas.

Many important real-world datasets come in the form of graphs or networks: social networks, knowledge graphs, protein-interaction networks, the World Wide Web, etc. (just to name a few). Yet, until recently, very little attention has been devoted to the generalization of neural network models to such structured datasets. In the last couple of years, a number of papers re-visited this problem of generalizing neural networks to work on arbitrarily structured graphs (Bruna et al., ICLR 2014; Henaff et al., 2015; Duvenaud et al., NIPS 2015; Li et al., ICLR 2016; Defferrard et al., NIPS 2016; Kipf & Welling, ICLR 2017), some of them now achieving very promising results in domains that have previously been dominated by, e.g., kernel-based methods, graph-based regularization techniques and others. In this post, I will give a brief overview of recent developments in this field and point out strengths and drawbacks of various approaches. I wrote a short comment on Ferenc's review here (at the very end of this post).

The 21st century is only two decades old and it is certain that one of the biggest transformative technologies and enablers for human society of this century is going to be Artificial intelligence (AI). It is a well-established idea that AI and associated services and platforms are set to transform global productivity, working patterns, and lifestyles and create enormous wealth. For example, McKinsey sees it delivering global economic activity of around $13 trillion by 2030. In the short-term, research firm Gartner expects the global AI-based economic activity to increase from about $1.2 trillion in 2018 to about $3.9 Trillion by 2022. It is no secret that this transformation is being, to a large extent, fueled by the powerful Machine Learning (ML) tools and techniques such as Deep Convolutional Networks, Generative Adversarial Networks (GAN), Gradient-boosted-tree models (GBM), Deep Reinforcement Learning (DRL), etc. However, traditional business and technology sectors are not the only fields being impacted by AI.

Natural language is hypothetically the best user interface for many domains. However, general models that provide an interface between natural language and any other domain still do not exist. Providing natural language interface to relational databases could possibly attract a vast majority of users that are or are not proficient with query languages. With the rise of deep learning techniques, there is extensive ongoing research in designing a suitable natural language interface to relational databases. This survey aims to overview some of the latest methods and models proposed in the area of SQL query generation from natural language. We describe models with various architectures such as convolutional neural networks, recurrent neural networks, pointer networks, reinforcement learning, etc. Several datasets intended to address the problem of SQL query generation are interpreted and briefly overviewed. In the end, evaluation metrics utilized in the field are presented mainly as a combination of execution accuracy and logical form accuracy.

Time is deeply woven into how people perceive, and communicate about the world. Almost unconsciously, we provide our language utterances with temporal cues, like verb tenses, and we can hardly produce sentences without such cues. Extracting temporal cues from text, and constructing a global temporal view about the order of described events is a major challenge of automatic natural language understanding. Temporal reasoning, the process of combining different temporal cues into a coherent temporal view, plays a central role in temporal information extraction. This article presents a comprehensive survey of the research from the past decades on temporal reasoning for automatic temporal information extraction from text, providing a case study on the integration of symbolic reasoning with machine learning-based information extraction systems.

Healthcare professionals have long envisioned using the enormous processing powers of computers to discover new facts and medical knowledge locked inside electronic health records. These vast medical archives contain time-resolved information about medical visits, tests and procedures, as well as outcomes, which together form individual patient journeys. By assessing the similarities among these journeys, it is possible to uncover clusters of common disease trajectories with shared health outcomes. The assignment of patient journeys to specific clusters may in turn serve as the basis for personalized outcome prediction and treatment selection. This procedure is a non-trivial computational problem, as it requires the comparison of patient data with multi-dimensional and multi-modal features that are captured at different times and resolutions. In this review, we provide a comprehensive overview of the tools and methods that are used in patient similarity analysis with longitudinal data and discuss its potential for improving clinical decision making.

Behavior Trees (BTs) were invented as a tool to enable modular AI in computer games, but have received an increasing amount of attention in the robotics community in the last decade. With rising demands on agent AI complexity, game programmers found that the Finite State Machines (FSM) that they used scaled poorly and were difficult to extend, adapt and reuse. In BTs, the state transition logic is not dispersed across the individual states, but organized in a hierarchical tree structure, with the states as leaves. This has a significant effect on modularity, which in turn simplifies both synthesis and analysis by humans and algorithms alike. These advantages are needed not only in game AI design, but also in robotics, as is evident from the research being done. In this paper we present a comprehensive survey of the topic of BTs in Artificial Intelligence and Robotic applications. The existing literature is described and categorized based on methods, application areas and contributions, and the paper is concluded with a list of open research challenges.

We study the efficient learnability of high-dimensional Gaussian mixtures in the outlier-robust setting, where a small constant fraction of the data is adversarially corrupted. We resolve the polynomial learnability of this problem when the components are pairwise separated in total variation distance. Specifically, we provide an algorithm that, for any constant number of components $k$, runs in polynomial time and learns the components of an $\epsilon$-corrupted $k$-mixture within information theoretically near-optimal error of $\tilde{O}(\epsilon)$, under the assumption that the overlap between any pair of components $P_i, P_j$ (i.e., the quantity $1-TV(P_i, P_j)$) is bounded by $\mathrm{poly}(\epsilon)$. Our separation condition is the qualitatively weakest assumption under which accurate clustering of the samples is possible. In particular, it allows for components with arbitrary covariances and for components with identical means, as long as their covariances differ sufficiently. Ours is the first polynomial time algorithm for this problem, even for $k=2$. Our algorithm follows the Sum-of-Squares based proofs to algorithms approach. Our main technical contribution is a new robust identifiability proof of clusters from a Gaussian mixture, which can be captured by the constant-degree Sum of Squares proof system. The key ingredients of this proof are a novel use of SoS-certifiable anti-concentration and a new characterization of pairs of Gaussians with small (dimension-independent) overlap in terms of their parameter distance.