The procedural generation of levels and content in video games is a challenging AI problem. Often such generation relies on an intelligent way of evaluating the content being generated so that constraints are satisfied and/or objectives maximized. In this work, we address the problem of creating levels that are not only playable but also revolve around specific mechanics in the game. We use constrained evolutionary algorithms and quality-diversity algorithms to generate small sections of Super Mario Bros levels called scenes, using three different simulation approaches: Limited Agents, Punishing Model, and Mechanics Dimensions. All three approaches are able to create scenes that give opportunity for a player to encounter or use targeted mechanics with different properties. We conclude by discussing the advantages and disadvantages of each approach and compare them to each other.

Understanding the dynamics of international politics is important yet challenging for civilians. In this work, we explore unsupervised neural models to infer relations between nations from news articles. We extend existing models by incorporating shallow linguistics information and propose a new automatic evaluation metric that aligns relationship dynamics with manually annotated key events. As understanding international relations requires carefully analyzing complex relationships, we conduct in-person human evaluations with three groups of participants. Overall, humans prefer the outputs of our model and give insightful feedback that suggests future directions for human-centered models. Furthermore, our model reveals interesting regional differences in news coverage. For instance, with respect to US-China relations, Singaporean media focus more on "strengthening" and "purchasing", while US media focus more on "criticizing" and "denouncing".

A neuroscience method to understanding the brain is to find and study the preferred stimuli that highly activate an individual cell or groups of cells. Recent advances in machine learning enable a family of methods to synthesize preferred stimuli that cause a neuron in an artificial or biological brain to fire strongly. Those methods are known as Activation Maximization (AM) [10] or Feature Visualization via Optimization. In this chapter, we (1) review existing AM techniques in the literature; (2) discuss a probabilistic interpretation for AM; and (3) review the applications of AM in debugging and explaining networks.

The emergence of deep learning networks raises a need for algorithms to explain their decisions so that users and domain experts can be confident using algorithmic recommendations for high-risk decisions. In this paper we leverage the information-rich latent space induced by such models to learn data representations or prototypes within such networks to elucidate their internal decision-making process. We introduce a novel application of case-based reasoning using prototypes to understand the decisions leading to the classification of time-series data, specifically investigating electrocardiogram (ECG) waveforms for classification of bradycardia, a slowing of heart rate, in infants. We improve upon existing models by explicitly optimizing for increased prototype diversity which in turn improves model accuracy by learning regions of the latent space that highlight features for distinguishing classes. We evaluate the hyperparameter space of our model to show robustness in diversity prototype generation and additionally, explore the resultant latent space of a deep classification network on ECG waveforms via an interactive tool to visualize the learned prototypical waveforms therein. We show that the prototypes are capable of learning real-world features - in our case-study ECG morphology related to bradycardia - as well as features within sub-classes. Our novel work leverages learned prototypical framework on two dimensional time-series data to produce explainable insights during classification tasks.

Two types of knowledge, triples from knowledge graphs and texts from unstructured documents, have been studied for knowledge aware open-domain conversation generation, in which triple attributes or graph paths can narrow down vertex candidates for knowledge selection decision, and texts can provide rich information for response generation. Fusion of a knowledge graph and texts might yield mutually reinforcing advantages for conversation generation, but there is less study on that. To address this challenge, we propose a knowledge aware chatting machine with three components, an augmented knowledge graph containing both triples and texts, knowledge selector, and response generator. For knowledge selection on the graph, we formulate it as a problem of multi-hop graph reasoning that is more explainable and flexible in comparison with previous works. To fully leverage long text information that differentiates our graph from others, we improve a state of the art reasoning algorithm with machine reading comprehension technology. We demonstrate that supported by such unified knowledge and explainable knowledge selection method, our system can generate more appropriate and informative responses than baselines.

In a recent article [1], Brette argues that coding as a concept is inappropriate for explanations of neurocognitive phenomena. Here, we argue that Brette's conceptual analysis mischaracterizes the structure of causal claims in coding and other forms of analysis-by-decomposition. We argue that analyses of this form are permissible, conceptually coherent, and offer essential tools for building and developing models of neurocognitive systems like the brain. Brette identifies three properties of coding: correspondence, representation, and causality. Brette grants correspondence but rejects both representation and causality for the neural code. While we disagree with his analyses of representation and causality, we limit our critique to the latter.

Big data solutions are designed to cope with data of huge Volume and wide Variety, that need to be ingested at high Velocity and have potential Veracity issues, challenging characteristics that are usually referred to as the "4Vs of Big Data". In order to evaluate possibly complex big data solutions, stress tests require to assess a large number of combinations of sub-components jointly with the possible big data variations. A formalization of the Design of Experiments (DoE) on big data solutions is aimed at ensuring the reproducibility of the experiments, facilitating their partitioning in sub-experiments and guaranteeing the consistency of their outcomes in a global assessment. In this paper, an ontology-based approach is proposed to support the evaluation of a big data system in two ways. Firstly, the approach formalizes a decomposition and recombination of the big data solution, allowing for the aggregation of component evaluation results at inter-component level. Secondly, existing work on DoE is translated into an ontology for supporting the selection of experiments. The proposed ontology-based approach offers the possibility to combine knowledge from the evaluation domain and the application domain. It exploits domain and inter-domain specific restrictions on the factor combinations in order to reduce the number of experiments. Contrary to existing approaches, the proposed use of ontologies is not limited to the assertional description and exploitation of past experiments but offers richer terminological descriptions for the development of a DoE from scratch. As an application example, a maritime big data solution to the problem of detecting and predicting vessel suspicious behaviour through mobility analysis is selected. The article is concluded with a sketch of future works.

TAMER has proven to be a powerful interactive reinforcement learning method for allowing ordinary people to teach and personalize autonomous agents' behavior by providing evaluative feedback. However, a TAMER agent planning with UCT---a Monte Carlo Tree Search strategy, can only update states along its path and might induce high learning cost especially for a physical robot. In this paper, we propose to drive the agent's exploration along the optimal path and reduce the learning cost by initializing the agent's reward function via inverse reinforcement learning from demonstration. We test our proposed method in the RL benchmark domain---Grid World---with different discounts on human reward. Our results show that learning from demonstration can allow a TAMER agent to learn a roughly optimal policy up to the deepest search and encourage the agent to explore along the optimal path. In addition, we find that learning from demonstration can improve the learning efficiency by reducing total feedback, the number of incorrect actions and increasing the ratio of correct actions to obtain an optimal policy, allowing a TAMER agent to converge faster.

The intention of the Workshop within the AI4D initiaitve in sub-Saharan Africa is to scope out the African ML/AI landscape, provide inputs for an African AI research roadmap, and support the development of cross-continent cooperation on AI for sustainable development. It is anticipated that the outcome of the workshop will be a Network of Excellence on AI for sub Saharan African researchers who focus on applications and research relating to AI and human development.

As Notre Dame Cathedral's majestic spire tumbled into the inferno on Monday night, live newsreaders around the world decried the tragic loss of this 12th-century marvel. The great timber roof – nicknamed "the forest" for the thousands of trees used in its beams – was gone, the rose windows feared melted, the heart of Paris destroyed forever. What few realised in the heat of the shocking footage was that much of what was ablaze was a 19th-century fantasy. Like most buildings of this age, Notre Dame is the sum of centuries of restorations and reinventions, a muddled patchwork of myth and speculation. Standing as a sturdy hulk on the banks of the Seine, the great stone pile has never been the most elegant or commanding of the ancient cathedrals, but it became the most famous. Begun in 1163, it was larger than any gothic church before it, employing some of the first flying buttresses to allow taller, thinner walls and larger expanses of glazing – including the spectacular rose windows that projected great cosmic wheels of colour into the luminous interior. "Where would [one] find … such magnificence and perfection, so high, so large, so strong, clothed round about with such a multiple variety of ornaments?"