Learning optimal feedback control laws capable of executing optimal trajectories is essential for many robotic applications. Such policies can be learned using reinforcement learning or planned using optimal control. While reinforcement learning is sample inefficient, optimal control only plans an optimal trajectory from a specific starting configuration. In this paper we propose deep optimal feedback control to learn an optimal feedback policy rather than a single trajectory. By exploiting the inherent structure of the robot dynamics and strictly convex action cost, we can derive principled cost functions such that the optimal policy naturally obeys the action limits, is globally optimal and stable on the training domain given the optimal value function. The corresponding optimal value function is learned end-to-end by embedding a deep differential network in the Hamilton-Jacobi-Bellmann differential equation and minimizing the error of this equality while simultaneously decreasing the discounting from short- to far-sighted to enable the learning. Our proposed approach enables us to learn an optimal feedback control law in continuous time, that in contrast to existing approaches generates an optimal trajectory from any point in state-space without the need of replanning. The resulting approach is evaluated on non-linear systems and achieves optimal feedback control, where standard optimal control methods require frequent replanning.

We propose a scheme for defending against adversarial attacks by suppressing the largest eigenvalue of the Fisher information matrix (FIM). Our starting point is one explanation on the rationale of adversarial examples. Based on the idea of the difference between a benign sample and its adversarial example is measured by the Euclidean norm, while the difference between their classification probability densities at the last (softmax) layer of the network could be measured by the Kullback-Leibler (KL) divergence, the explanation shows that the output difference is a quadratic form of the input difference. If the eigenvalue of this quadratic form (a.k.a. FIM) is large, the output difference becomes large even when the input difference is small, which explains the adversarial phenomenon. This makes the adversarial defense possible by controlling the eigenvalues of the FIM. Our solution is adding one term representing the trace of the FIM to the loss function of the original network, as the largest eigenvalue is bounded by the trace. Our defensive scheme is verified by experiments using a variety of common attacking methods on typical deep neural networks, e.g. LeNet, VGG and ResNet, with datasets MNIST, CIFAR-10, and German Traffic Sign Recognition Benchmark (GTSRB). Our new network, after adopting the novel loss function and retraining, has an effective and robust defensive capability, as it decreases the fooling ratio of the generated adversarial examples, and remains the classification accuracy of the original network.

Credit scoring models support loan approval decisions in the financial services industry. Lenders train these models on data from previously granted credit applications, where the borrowers' repayment behavior has been observed. This approach creates sample bias. The scoring model (i.e., classifier) is trained on accepted cases only. Applying the resulting model to screen credit applications from the population of all borrowers degrades model performance. Reject inference comprises techniques to overcome sampling bias through assigning labels to rejected cases. The paper makes two contributions. First, we propose a self-learning framework for reject inference. The framework is geared toward real-world credit scoring requirements through considering distinct training regimes for iterative labeling and model training. Second, we introduce a new measure to assess the effectiveness of reject inference strategies. Our measure leverages domain knowledge to avoid artificial labeling of rejected cases during strategy evaluation. We demonstrate this approach to offer a robust and operational assessment of reject inference strategies. Experiments on a real-world credit scoring data set confirm the superiority of the adjusted self-learning framework over regular self-learning and previous reject inference strategies. We also find strong evidence in favor of the proposed evaluation measure assessing reject inference strategies more reliably, raising the performance of the eventual credit scoring model.

As part of a quality control process in manufacturing it is often necessary to test whether all parts of a product satisfy a required property, with as few inspections as possible. When multiple inspection apparatuses with different costs and precision exist, it is desirable that testing can be carried out cost-effectively by properly controlling the trade-off between the costs and the precision. In this paper, we formulate this as a level set estimation (LSE) problem under cost-dependent input uncertainty - LSE being a type of active learning for estimating the level set, i.e., the subset of the input space in which an unknown function value is greater or smaller than a pre-determined threshold. Then, we propose a new algorithm for LSE under cost-dependent input uncertainty with theoretical convergence guarantee. We demonstrate the effectiveness of the proposed algorithm by applying it to synthetic and real datasets.

In this paper, we explore various statistical techniques for anomaly detection in conjunction with the popular Long Short-Term Memory (LSTM) deep learning model for transportation networks. We obtain the prediction errors from an LSTM model, and then apply three statistical models based on (i) the Gaussian distribution, (ii) Extreme Value Theory (EVT), and (iii) the Tukey's method. Using statistical tests and numerical studies, we find strong evidence against the widely employed Gaussian distribution based detection rule on the prediction errors. Next, motivated by fundamental results from Extreme Value Theory, we propose a detection technique that does not assume any parent distribution on the prediction errors. Through numerical experiments conducted on several real-world traffic data sets, we show that the EVT-based detection rule is superior to other detection rules, and is supported by statistical evidence.

Entity resolution (ER) (record linkage or de-duplication) is the process of merging together noisy databases, often in the absence of a unique identifier. A major advancement in ER methodology has been the application of Bayesian generative models. Such models provide a natural framework for clustering records to unobserved (latent) entities, while providing exact uncertainty quantification and tight performance bounds. Despite these advancements, existing models do not scale to realistically-sized databases (larger than 1000 records) and they do not incorporate probabilistic blocking. In this paper, we propose "distributed Bayesian linkage" or d-blink -- the first scalable and distributed end-to-end Bayesian model for ER, which propagates uncertainty in blocking, matching and merging. We make several novel contributions, including: (i) incorporating probabilistic blocking directly into the model through auxiliary partitions; (ii) support for missing values; (iii) a partially-collapsed Gibbs sampler; and (iv) a novel perturbation sampling algorithm (leveraging the Vose-Alias method) that enables fast updates of the entity attributes. Finally, we conduct experiments on five data sets which show that d-blink can achieve significant efficiency gains -- in excess of 300$\times$ -- when compared to existing non-distributed methods.

Time series classification (TSC) is the area of machine learning interested in learning how to assign labels to time series. The last few decades of work in this area have led to significant progress in the accuracy of classifiers, with the state of the art now represented by the HIVE-COTE algorithm. While extremely accurate, HIVE-COTE is infeasible to use in many applications because of its very high training time complexity in O(N^2*T^4) for a dataset with N time series of length T. For example, it takes HIVE-COTE more than 72,000s to learn from a small dataset with N=700 time series of short length T=46. Deep learning, on the other hand, has now received enormous attention because of its high scalability and state-of-the-art accuracy in computer vision and natural language processing tasks. Deep learning for TSC has only very recently started to be explored, with the first few architectures developed over the last 3 years only. The accuracy of deep learning for TSC has been raised to a competitive level, but has not quite reached the level of HIVE-COTE. This is what this paper achieves: outperforming HIVE-COTE's accuracy together with scalability. We take an important step towards finding the AlexNet network for TSC by presenting InceptionTime---an ensemble of deep Convolutional Neural Network (CNN) models, inspired by the Inception-v4 architecture. Our experiments show that InceptionTime slightly outperforms HIVE-COTE with a win/draw/loss on the UCR archive of 40/6/39. Not only is InceptionTime more accurate, but it is much faster: InceptionTime learns from that same dataset with 700 time series in 2,300s but can also learn from a dataset with 8M time series in 13 hours, a quantity of data that is fully out of reach of HIVE-COTE.

While machine learning is rapidly being developed and deployed in health settings such as influenza prediction, there are critical challenges in using data from one environment in another due to variability in features; even within disease labels there can be differences (e.g. "fever" may mean something different reported in a doctor's office versus in an online app). Moreover, models are often built on passive, observational data which contain different distributions of population subgroups (e.g. men or women). Thus, there are two forms of instability between environments in this observational transport problem. We first harness knowledge from health to conceptualize the underlying causal structure of this problem in a health outcome prediction task. Based on sources of stability in the model, we posit that for human-sourced data and health prediction tasks we can combine environment and population information in a novel population-aware hierarchical Bayesian domain adaptation framework that harnesses multiple invariant components through population attributes when needed. We study the conditions under which invariant learning fails, leading to reliance on the environment-specific attributes. Experimental results for an influenza prediction task on four datasets gathered from different contexts show the model can improve prediction in the case of largely unlabelled target data from a new environment and different constituent population, by harnessing both environment and population invariant information. This work represents a novel, principled way to address a critical challenge by blending domain (health) knowledge and algorithmic innovation. The proposed approach will have a significant impact in many social settings wherein who and where the data comes from matters.

Previous deep learning based approaches for the task mainly adopt the Compare-Aggregate architecture that performs word-level comparison followed by aggregation. In this work, we take a departure from the popular Compare-Aggregate architecture, and instead, propose a new gated self-attention memory network for the task. Combined with a simple transfer learning technique from a large-scale online corpus, our model outperforms previous methods by a large margin, achieving new state-of- the-art results on two standard answer selection datasets: TrecQA and WikiQA. 1 Introduction and Related Work Answer selection is an important task, with applications in many areas (Lai et al., 2018). Given a question and a set of candidate answers, the task is to identify the most relevant candidate. Previous work on answer selection typically relies on feature engineering, linguistic tools, or external resources (Wang et al., 2007; Wang and Manning, 2010; Heilman and Smith, 2010; Yih et al., 2013; Y ao et al., 2013).

The work presented in this paper aims to explore how, and to what extent, an adaptive robotic coach has the potential to provide extra motivation to adhere to long-term rehabilitation and help fill the coaching gap which occurs during repetitive solo practice in high performance sport. Adapting the behavior of a social robot to a specific user, using reinforcement learning (RL), could be a way of increasing adherence to an exercise routine in both domains. The requirements gathering phase is underway and is presented in this paper along with the rationale of using RL in this context.