We propose a novel regularization method, called \textit{volumization}, for neural networks. Inspired by physics, we define a physical volume for the weight parameters in neural networks, and we show that this method is an effective way of regularizing neural networks. Intuitively, this method interpolates between an $L_2$ and $L_\infty$ regularization. Therefore, weight decay and weight clipping become special cases of the proposed algorithm. We prove, on a toy example, that the essence of this method is a regularization technique to control bias-variance tradeoff. The method is shown to do well in the categories where the standard weight decay method is shown to work well, including improving the generalization of networks and preventing memorization. Moreover, we show that the volumization might lead to a simple method for training a neural network whose weight is binary or ternary.

We study how state-of-the-art neural networks for 3D object detection using a single-stage pipeline can be made safety aware. We start with the safety specification (reflecting the capability of other components) that partitions the 3D input space by criticality, where the critical area employs a separate criterion on robustness under perturbation, quality of bounding boxes, and the tolerance over false negatives demonstrated on the training set. In the architecture design, we consider symbolic error propagation to allow feature-level perturbation. Subsequently, we introduce a specialized loss function reflecting (1) the safety specification, (2) the use of single-stage detection architecture, and finally, (3) the characterization of robustness under perturbation. We also replace the commonly seen non-max-suppression post-processing algorithm by a safety-aware non-max-inclusion algorithm, in order to maintain the safety claim created by the neural network. The concept is detailed by extending the state-of-the-art PIXOR detector which creates object bounding boxes in bird's eye view with inputs from point clouds.

In this manuscript, we provide a structured and comprehensive overview of techniques to integrate machine learning with physics-based modeling. First, we provide a summary of application areas for which these approaches have been applied. Then, we describe classes of methodologies used to construct physics-guided machine learning models and hybrid physics-machine learning frameworks from a machine learning standpoint. With this foundation, we then provide a systematic organization of these existing techniques and discuss ideas for future research.

Conformance checking encompasses a body of process mining techniques which aim to find and describe the differences between a process model capturing the expected process behavior and a corresponding event log recording the observed behavior. Alignments are an established technique to compute the distance between a trace in the event log and the closest execution trace of a corresponding process model. Given a cost function, an alignment is optimal when it contains the least number of mismatches between a log trace and a model trace. Determining optimal alignments, however, is computationally expensive, especially in light of the growing size and complexity of event logs from practice, which can easily exceed one million events with traces of several hundred activities. A common limitation of existing alignment techniques is the inability to exploit repetitions in the log. By exploiting a specific form of sequential pattern in traces, namely tandem repeats, we propose a novel technique that uses pre- and post-processing steps to compress the length of a trace and recomputes the alignment cost while guaranteeing that the cost result never under-approximates the optimal cost. In an extensive empirical evaluation with 50 real-life model-log pairs and against five state-of-the-art alignment techniques, we show that the proposed compression approach systematically outperforms the baselines by up to an order of magnitude in the presence of traces with repetitions, and that the cost over-approximation, when it occurs, is negligible.

We demonstrate the first reinforcement-learning application for robots equipped with an event camera. Because of the considerably lower latency of the event camera, it is possible to achieve much faster control of robots compared with the existing vision-based reinforcement-learning applications using standard cameras. To handle a stream of events for reinforcement learning, we introduced an image-like feature and demonstrated the feasibility of training an agent in a simulator for two tasks: fast collision avoidance and obstacle tracking. Finally, we set up a robot with an event camera in the real world and then transferred the agent trained in the simulator, resulting in successful fast avoidance of randomly thrown objects. Incorporating event camera into reinforcement learning opens new possibilities for various robotics applications that require swift control, such as autonomous vehicles and drones, through end-to-end learning approaches.

In public media as well as in scientific publications, the term \emph{bias} is used in conjunction with machine learning in many different contexts, and with many different meanings. This paper proposes a taxonomy of these different meanings, terminology, and definitions by surveying the, primarily scientific, literature on machine learning. In some cases, we suggest extensions and modifications to promote a clear terminology and completeness. The survey is followed by an analysis and discussion on how different types of biases are connected and depend on each other. We conclude that there is a complex relation between bias occurring in the machine learning pipeline that leads to a model, and the eventual bias of the model (which is typically related to social discrimination). The former bias may or may not influence the latter, in a sometimes bad, and sometime good way.

Recommender systems are software applications that help users to find items of interest in situations of information overload. Current research often assumes a one-shot interaction paradigm, where the users' preferences are estimated based on past observed behavior and where the presentation of a ranked list of suggestions is the main, one-directional form of user interaction. Conversational recommender systems (CRS) take a different approach and support a richer set of interactions. These interactions can, for example, help to improve the preference elicitation process or allow the user to ask questions about the recommendations and to give feedback. The interest in CRS has significantly increased in the past few years. This development is mainly due to the significant progress in the area of natural language processing, the emergence of new voice-controlled home assistants, and the increased use of chatbot technology. With this paper, we provide a detailed survey of existing approaches to conversational recommendation. We categorize these approaches in various dimensions, e.g., in terms of the supported user intents or the knowledge they use in the background. Moreover, we discuss technological approaches, review how CRS are evaluated, and finally identify a number of gaps that deserve more research in the future.

The Obstacle Tower Challenge is the task to master a procedurally generated chain of levels that subsequently get harder to complete. Whereas the top 6 performing entries of last year's competition all used human demonstrations to learn how to cope with the challenge, we present an approach that performed competitively (placed 7th) but starts completely from scratch by means of Deep Reinforcement Learning with a relatively simple feed-forward deep network structure. We especially look at the generalization performance of the taken approach concerning different seeds and various visual themes that have become available after the competition, and investigate where the agent fails and why. Note that our approach does not possess a short-term memory like employing recurrent hidden states. With this work, we hope to contribute to a better understanding of what is possible with a relatively simple, flexible solution that can be applied to learning in environments featuring complex 3D visual input where the abstract task structure itself is still fairly simple.

Model-free deep reinforcement learning (RL) has demonstrated its superiority on many complex sequential decision-making problems. However, heavy dependence on dense rewards and high sample-complexity impedes the wide adoption of these methods in real-world scenarios. On the other hand, imitation learning (IL) learns effectively in sparse-rewarded tasks by leveraging the existing expert demonstrations. In practice, collecting a sufficient amount of expert demonstrations can be prohibitively expensive, and the quality of demonstrations typically limits the performance of the learning policy. In this work, we propose Self-Adaptive Imitation Learning (SAIL) that can achieve (near) optimal performance given only a limited number of sub-optimal demonstrations for highly challenging sparse reward tasks. SAIL bridges the advantages of IL and RL to reduce the sample complexity substantially, by effectively exploiting sup-optimal demonstrations and efficiently exploring the environment to surpass the demonstrated performance. Extensive empirical results show that not only does SAIL significantly improve the sample-efficiency but also leads to much better final performance across different continuous control tasks, comparing to the state-of-the-art.

We consider a fully cooperative multi-agent system where agents cooperate to maximize a system's utility in a partial-observable environment. We propose that multi-agent systems must have the ability to (1) communicate and understand the inter-plays between agents and (2) correctly distribute rewards based on an individual agent's contribution. In contrast, most work in this setting considers only one of the above abilities. In this study, we develop an architecture that allows for communication among agents and tailors the system's reward for each individual agent. Our architecture represents agent communication through graph convolution and applies an existing credit assignment structure, counterfactual multi-agent policy gradient (COMA), to assist agents to learn communication by back-propagation. The flexibility of the graph structure enables our method to be applicable to a variety of multi-agent systems, e.g. dynamic systems that consist of varying numbers of agents and static systems with a fixed number of agents. We evaluate our method on a range of tasks, demonstrating the advantage of marrying communication with credit assignment. In the experiments, our proposed method yields better performance than the state-of-art methods, including COMA. Moreover, we show that the communication strategies offers us insights and interpretability of the system's cooperative policies.