Apart from discriminative models for classification and object detection tasks, the application of deep convolutional neural networks to basic research utilizing natural imaging data has been somewhat limited; particularly in cases where a set of interpretable features for downstream analysis is needed, a key requirement for many scientific investigations. We present an algorithm and training paradigm designed specifically to address this: decontextualized hierarchical representation learning (DHRL). By combining a generative model chaining procedure with a ladder network architecture and latent space regularization for inference, DHRL address the limitations of small datasets and encourages a disentangled set of hierarchically organized features. In addition to providing a tractable path for analyzing complex hierarchal patterns using variation inference, this approach is generative and can be directly combined with empirical and theoretical approaches. To highlight the extensibility and usefulness of DHRL, we demonstrate this method in application to a question from evolutionary biology.

Reinforcement learning and probabilistic reasoning algorithms aim at learning from interaction experiences and reasoning with probabilistic contextual knowledge respectively. In this research, we develop algorithms for robot task completions, while looking into the complementary strengths of reinforcement learning and probabilistic reasoning techniques. The robots learn from trial-and-error experiences to augment their declarative knowledge base, and the augmented knowledge can be used for speeding up the learning process in potentially different tasks. We have implemented and evaluated the developed algorithms using mobile robots conducting dialog and navigation tasks. From the results, we see that our robot's performance can be improved by both reasoning with human knowledge and learning from task-completion experience. More interestingly, the robot was able to learn from navigation tasks to improve its dialog strategies.

In this paper we describe a concept-wise multi-preference semantics for description logic which has its root in the preferential approach for modeling defeasible reasoning in knowledge representation. We argue that this proposal, beside satisfying some desired properties, such as KLM postulates, and avoiding the drowning problem, also defines a plausible notion of semantics. We motivate the plausibility of the concept-wise multi-preference semantics by developing a logical semantics of self-organising maps, which have been proposed as possible candidates to explain the psychological mechanisms underlying category generalisation, in terms of multi-preference interpretations.

In today's software development industry, jobs have become more cognitively complex and require workers who are more collaborative and creative in their problem-solving techniques.14 Employees also must be able to combine diverse specializations rather than just having routine knowledge in one domain.22 While the "hard" technical skills associated with programming remain a prerequisite for new hires, the industry also wants software developers who can readily demonstrate a range of so-called "soft" skills, including the capacity to communicate clearly, facilitate an open and inclusive workplace environment, and demonstrate the resiliency and flexibility to work on a range of tasks.24 Our own past research4 interviewing software industry hiring managers indicates that discerning such soft skills among new hires is an overwhelming priority across companies. The industry hiring managers and directors we interviewed over the past two years stated that while the capacity to code is a necessity for employment, these managers actually spend the vast majority of their recruitment time assessing a candidate's soft skills, as these suggest the presence of adaptive expertise (AE) and the candidate's potential for persistence and continual learning on the job.4 What was also intriguing to us in discussion with a wide range of hiring managers was their expressed willingness to consider graduates from alternative educational settings--in particular, so-called "coding bootcamps"--alongside more traditional hires from undergraduate computer science (CS) programs.4 While there is no single representative model of a coding bootcamp, these intense training programs extend, on average,14 weeks in duration, cost approximately $12,000, and emphasize teaching the programming skills that employers look for from new software developer hires (particularly front-end programming) while also enabling their graduates to grasp the most essential aspects of coding.6 Much of this expressed willingness to hire codecamp graduates stemmed directly back to hiring managers' perceptions that what boot-camp students may lack in rigorous CS knowledge is counterbalanced with greater work experience and the interpersonal and intrapersonal skills to join a wider team while remaining resilient in the face of unexpected challenges. This, of course, represented only one party's perspective.

Quantum computers can be used for supervised learning by treating parametrised quantum circuits as models that map data inputs to predictions. While a lot of work has been done to investigate practical implications of this approach, many important theoretical properties of these models remain unknown. Here we investigate how the strategy with which data is encoded into the model influences the expressive power of parametrised quantum circuits as function approximators. We show that one can naturally write a quantum model as a partial Fourier series in the data, where the accessible frequencies are determined by the nature of the data encoding gates in the circuit. By repeating simple data encoding gates multiple times, quantum models can access increasingly rich frequency spectra. We show that there exist quantum models which can realise all possible sets of Fourier coefficients, and therefore, if the accessible frequency spectrum is asymptotically rich enough, such models are universal function approximators.

This paper investigates the feasibility of automated reasoning over temporal DL-Lite (TDL-Lite) knowledge bases (KBs). We test the usage of off-the-shelf LTL reasoners to check satisfiability of TDL-Lite KBs. In particular, we test the robustness and the scalability of reasoners when dealing with TDL-Lite TBoxes paired with a temporal ABox. We conduct various experiments to analyse the performance of different reasoners by randomly generating TDL-Lite KBs and then measuring the running time and the size of the translations. Furthermore, in an effort to make the usage of TDL-Lite KBs a reality, we present a fully fledged tool with a graphical interface to design them. Our interface is based on conceptual modelling principles and it is integrated with our translation tool and a temporal reasoner.

Answer Set Programming (ASP) has become a popular and quite sophisticated approach to declarative problem solving. This is arguably due to its attractive modeling-grounding-solving workflow that provides an easy approach to problem solving, even for laypersons outside computer science. Unlike this, the high degree of sophistication of the underlying technology makes it increasingly hard for ASP experts to put ideas into practice. For addressing this issue, this tutorial aims at enabling users to build their own ASP-based systems. More precisely, we show how the ASP system CLINGO can be used for extending ASP and for implementing customized special-purpose systems. To this end, we propose two alternatives. We begin with a traditional AI technique and show how meta programming can be used for extending ASP. This is a rather light approach that relies on CLINGO's reification feature to use ASP itself for expressing new functionalities. Unlike this, the major part of this tutorial uses traditional programming (in PYTHON) for manipulating CLINGO via its application programming interface. This approach allows for changing and controlling the entire model-ground-solve workflow of ASP. Central to this is CLINGO's new Application class that allows us to draw on CLINGO's infrastructure by customizing processes similar to the one in CLINGO. For instance, we may engage manipulations to programs' abstract syntax trees, control various forms of multi-shot solving, and set up theory propagators for foreign inferences. Another cross-sectional structure, spanning meta as well as application programming, is CLINGO's intermediate format, ASPIF, that specifies the interface among the underlying grounder and solver. We illustrate the aforementioned concepts and techniques throughout this tutorial by means of examples and several non-trivial case-studies.

The focus of the 2018 Logic and Practice of Programming workshop was on logic and declarative languages for the practice of programming. Of particular interest were languages (1) that have a clear semantic foundation, so that they can be used for concise modeling of complex application problems, facilitating formal proofs and automated analysis, and (2) that are also implementable, so that the implementations can run as specified, as part of real applications. Also of interest were (a) the design of declarative languages, libraries, and tools that facilitate the construction of complex systems and applications, (b) approaches to integrate declarative and procedural programming, and (c) the use of declarative languages to facilitate other programming paradigms, e.g., distributed programming. The target audience for these languages was students who wish to model complex application problems, and practitioners who want to use them. The goal of the workshop was to bring together the best people and best languages, tools, and ideas to help improve logic languages for the practice of programming and to improve the practice of programming with logic and declarative programming.

In-person competition is a no-go in many disciplines amid the COVID-19 pandemic, but speed cubers will be still able to battle opponents remotely in the Rubik's Cube World Cup. Rubik's has revealed the Connected Cube, which links to your phone or tablet and tracks your solve times and progress in real-time. It's more of a traditional cube than GoCube, which is largely a STEM-focused toy. Both use the same platform and can connect to the Rubik's Arena community, which has almost 47,000 players. As such, amateur and professional cubers can take part in this year's World Cup without having to travel, as long as they have a Connected Cube or GoCube. Qualifiers start August 15th and run through October 10th.

This paper studies novel subgoaling relaxations for automated planning with propositional and numeric state variables. Subgoaling relaxations address one source of complexity of the planning problem: the requirement to satisfy conditions simultaneously. The core idea is to relax this requirement by recursively decomposing conditions into atomic subgoals that are considered in isolation. Such relaxations are typically used for pruning, or as the basis for computing admissible or inadmissible heuristic estimates to guide optimal or satisificing heuristic search planners. In the last decade or so, the subgoaling principle has underpinned the design of an abundance of relaxation-based heuristics whose formulations have greatly extended the reach of classical planning. This paper extends subgoaling relaxations to support numeric state variables and numeric conditions. We provide both theoretical and practical results, with the aim of reaching a good trade-off between accuracy and computation costs within a heuristic state-space search planner. Our experimental results validate the theoretical assumptions, and indicate that subgoaling substantially improves on the state of the art in optimal and satisficing numeric planning via forward state-space search.