Describing or calculating the conditional probabilities of multiple events is exponentially expensive. In this work, a natural generalization of Bayesian belief network is proposed by incorporating with tensor network, which is dubbed as Bayesian tensor network (BTN), to efficiently describe the conditional probabilities among multiple sets of events. The complexity of BTN that gives the conditional probabilities of $M$ sets of events scales only polynomially with $M$. To testify its validity, BTN is implemented to capture the conditional probabilities between images and their classifications, where each feature is mapped to a probability distribution of a set of mutually exclusive events. A rotation optimization method is suggested to update BTN, which avoids gradient vanishing problem and exhibits high efficiency. With a simple tree network structures, BTN exhibits competitive performances on fashion-MNIST dataset. Analogous to the tensor network simulations of quantum systems, the validity of BTN implies an "area law" of fluctuations in image recognition problems.

Despite the recent successes of deep learning, such models are still far from some human abilities like learning from few examples, reasoning and explaining decisions. In this paper, we focus on organ annotation in medical images and we introduce a reasoning framework that is based on learning fuzzy relations on a small dataset for generating explanations. Given a catalogue of relations, it efficiently induces the most relevant relations and combines them for building constraints in order to both solve the organ annotation task and generate explanations. We test our approach on a publicly available dataset of medical images where several organs are already segmented. A demonstration of our model is proposed with an example of explained annotations. It was trained on a small training set containing as few as a couple of examples.

Deep neural networks (DNN) are versatile parametric models utilised successfully in a diverse number of tasks and domains. However, they have limitations---particularly from their lack of robustness and over-sensitivity to out of distribution samples. Bayesian Neural Networks, due to their formulation under the Bayesian framework, provide a principled approach to building neural networks that address these limitations. This paper describes a study that empirically evaluates and compares Bayesian Neural Networks to their equivalent point estimate Deep Neural Networks to quantify the predictive uncertainty induced by their parameters, as well as their performance in view of this uncertainty. In this study, we evaluated and compared three point estimate deep neural networks against comparable Bayesian neural network alternatives using two well-known benchmark image classification datasets (CIFAR-10 and SVHN).

As in any interaction process, misunderstandings, ambiguity, and failures to correctly understand the interaction partner are bound to happen in human-robot interaction. We term these failures 'conflicts' and are interested in both conflict detection and conflict resolution. In that, we focus on the robot's perspective. For the robot, conflicts may occur because of errors in its perceptual processes or because of ambiguity stemming from human input. This poster presents a brief system overview, and details Here, we briefly outline the project's motivation and setting, introduce the general processing framework, and then present two kinds of conflicts in some more detail: 1) a failure to identify a relevant object at all; 2) ambiguity emerging from multiple matches in scene perception.

This paper introduces a new approach to learning from i.i.d. data under model miss-specification. This approach casts the problem of learning as minimizing the expected code-length of a Bayesian mixture code. To solve this problem, we build on PAC-Bayes bounds, information theory and a new family of second-order Jensen bounds. The key insight of this paper is that the use of the standard (first-order) Jensen bounds in learning is suboptimal when our model class is miss-specified (i.e. it does not contain the data generating distribution). As a consequence of this insight, this work provides strong theoretical arguments explaining why the Bayesian posterior is not optimal for making predictions that generalize under model miss-specification because the Bayesian posterior is directly related to the use of first-order Jensen bounds. We then argue for the use of second-order Jensen bounds, which leads to new families of learning algorithms. In this work, we introduce novel variational and ensemble learning methods based on the minimization of a novel family of second-order PAC-Bayes bounds over the expected code-length of a Bayesian mixture code. Using this new framework, we also provide novel hypotheses of why parameters in a flat minimum generalize better than parameters in a sharp minimum.

The family of methods collectively known as classifier chains has become a popular approach to multi-label learning problems. This approach involves linking together off-the-shelf binary classifiers in a chain structure, such that class label predictions become features for other classifiers. Such methods have proved flexible and effective and have obtained state-of-the-art empirical performance across many datasets and multi-label evaluation metrics. This performance led to further studies of how exactly it works, and how it could be improved, and in the recent decade numerous studies have explored classifier chains mechanisms on a theoretical level, and many improvements have been made to the training and inference procedures, such that this method remains among the state-of-the-art options for multi-label learning. Given this past and ongoing interest, which covers a broad range of applications and research themes, the goal of this work is to provide a review of classifier chains, a survey of the techniques and extensions provided in the literature, as well as perspectives for this approach in the domain of multi-label classification in the future. We conclude positively, with a number of recommendations for researchers and practitioners, as well as outlining a number of areas for future research.

Over the past two decades, Machine Learning (ML) techniques have been increasingly utilized for the purpose of predicting outcomes in sport. In this paper, we provide a review of studies that have used ML for predicting results in team sport, covering studies from 1996 to 2019. We sought to answer five key research questions while extensively surveying papers in this field. This paper offers insights into which ML algorithms have tended to be used in this field, as well as those that are beginning to emerge with successful outcomes. Our research highlights defining characteristics of successful studies and identifies robust strategies for evaluating accuracy results in this application domain. Our study considers accuracies that have been achieved across different sports and explores the notion that outcomes of some team sports could be inherently more difficult to predict than others. Finally, our study uncovers common themes of future research directions across all surveyed papers, looking for gaps and opportunities, while proposing recommendations for future researchers in this domain.

To study users' travel behaviour and travel time between origin and destination, researchers employ travel surveys. Although there is consensus in the field about the potential, after over ten years of research and field experimentation, Smartphone-based travel surveys still did not take off to a large scale. Here, computer intelligence algorithms take the role that operators have in Traditional Travel Surveys; since we train each algorithm on data, performances rest on the data quality, thus on the ground truth. Inaccurate validations affect negatively: labels, algorithms' training, travel diaries precision, and therefore data validation, within a very critical loop. Interestingly, boundaries are proven burdensome to push even for Machine Learning methods. To support optimal investment decisions for practitioners, we expose the drivers they should consider when assessing what they need against what they get. This paper highlights and examines the critical aspects of the underlying research and provides some recommendations: (i) from the device perspective, on the main physical limitations; (ii) from the application perspective, the methodological framework deployed for the automatic generation of travel diaries; (iii)from the ground truth perspective, the relationship between user interaction, methods, and data.

Published as a conference paper at ICLR 2020M ETA-L EARNING WITHOUT M EMORIZATION Mingzhang Yin 12, George T ucker 2, Mingyuan Zhou 1, Sergey Levine 23, Chelsea Finn 24 mzyin@utexas.edu, Meta-learning has emerged as a promising technique for leveraging data from previous tasks to enable efficient learning of new tasks. However, most meta-learning algorithms implicitly require that the meta-training tasks be mutually-exclusive, such that no single model can solve all of the tasks at once. For example, when creating tasks for few-shot image classification, prior work uses a per-task random assignment of image classes to N-way classification labels. If this is not done, the meta-learner can ignore the task training data and learn a single model that performs all of the meta-training tasks zero-shot, but does not adapt effectively to new image classes. This requirement means that the user must take great care in designing the tasks, for example by shuffling labels or removing task identifying information from the inputs. In some domains, this makes meta-learning entirely inapplicable. In this paper, we address this challenge by designing a meta-regularization objective using information theory that places precedence on data-driven adaptation. This causes the meta-learner to decide what must be learned from the task training data and what should be inferred from the task testing input. By doing so, our algorithm can successfully use data from non-mutually-exclusive tasks to efficiently adapt to novel tasks. We demonstrate its applicability to both contextual and gradient-based meta-learning algorithms, and apply it in practical settings where applying standard meta-learning has been difficult. Our approach substantially outperforms standard meta-learning algorithms in these settings. Meta-learning (Schmidhuber, 1987) has emerged as a promising approach for enabling systems to quickly learn new tasks by building upon experience from previous related tasks (Thrun & Pratt, 2012; Koch et al., 2015; Santoro et al., 2016; Ravi & Larochelle, 2016; Finn et al., 2017). Meta-learning accomplishes this by explicitly optimizing for few-shot generalization across a set of meta-training tasks. The meta-learner is trained such that, after being presented with a small task training set, it can accurately make predictions on test datapoints for that meta-training task.

We propose a general method for constructing hypothesis tests and confidence sets that have finite sample guarantees without regularity conditions. We refer to such procedures as ``universal.'' The method is very simple and is based on a modified version of the usual likelihood ratio statistic, that we call ``the split likelihood ratio test'' (split LRT). The method is especially appealing for irregular statistical models. Canonical examples include mixture models and models that arise in shape-constrained inference. %mixture models and shape-constrained models are just two examples. Constructing tests and confidence sets for such models is notoriously difficult. Typical inference methods, like the likelihood ratio test, are not useful in these cases because they have intractable limiting distributions. In contrast, the method we suggest works for any parametric model and also for some nonparametric models. The split LRT can also be used with profile likelihoods to deal with nuisance parameters, and it can also be run sequentially to yield anytime-valid $p$-values and confidence sequences.