This paper presents BiPaR, a bilingual parallel novel-style machine reading comprehension (MRC) dataset, developed to support multilingual and cross-lingual reading comprehension. The biggest difference between BiPaR and existing reading comprehension datasets is that each triple (Passage, Question, Answer) in BiPaR is written parallelly in two languages. We collect 3,667 bilingual parallel paragraphs from Chinese and English novels, from which we construct 14,668 parallel question-answer pairs via crowdsourced workers following a strict quality control procedure. We analyze BiPaR in depth and find that BiPaR offers good diversification in prefixes of questions, answer types and relationships between questions and passages. We also observe that answering questions of novels requires reading comprehension skills of coreference resolution, multi-sentence reasoning, and understanding of implicit causality, etc. With BiPaR, we build monolingual, multilingual, and cross-lingual MRC baseline models. Even for the relatively simple monolingual MRC on this dataset, experiments show that a strong BERT baseline is over 30 points behind human in terms of both EM and F1 score, indicating that BiPaR provides a challenging testbed for monolingual, multilingual and cross-lingual MRC on novels. The dataset is available at https://multinlp.github.io/BiPaR/.

Generalized planning is the task of generating a single solution that is valid for a set of planning problems. In this paper we show how to represent and compute generalized plans using procedural Domain Control Knowledge (DCK). We define a {\it divide and conquer} approach that first generates the procedural DCK solving a set of planning problems representative of certain subtasks and then compile it as callable procedures of the overall generalized planning problem. Our procedure calling mechanism allows nested and recursive procedure calls and is implemented in PDDL so that classical planners can compute and exploit procedural DCK. Experiments show that an off-the-shelf classical planner, using procedural DCK as callable procedures, can compute generalized plans in a wide range of domains including non-trivial ones, such as sorting variable-size lists or DFS traversal of binary trees with variable size.

October 14, 2019 A BSTRACT Expressivity is one of the most significant issues in assessing neural networks. In this paper, we provide a quantitative analysis of the expressivity from dynamic models, where Hilbert space is employed to analyze its convergence and criticality. From the feature mapping of several widely used activation functions made by Hermite polynomials, We found sharp declines or even saddle points in the feature space, which stagnate the information transfer in deep neural networks, then present an activation function design based on the Hermite polynomials for better utilization of spatial representation. Moreover, we analyze the information transfer of deep neural networks, emphasizing the convergence problem caused by the mismatch between input and topological structure. We also study the effects of input perturbations and regularization operators on critical expressivity. Finally, we verified the proposed method by multivariate time series prediction. The results show that the optimized DeepESN provides higher predictive performance, especially for long-term prediction. Our theoretical analysis reveals that deep neural networks use spatial domains for information representation and evolve to the edge of chaos as depth increases. In actual training, whether a particular network can ultimately arrive that depends on its ability to overcome convergence and pass information to the required network depth. K eywords Deep neural networks; expressivity; criticality theory; convergence; activation function; Hilbert transform 1 Introduction Deep neural networks (DNNs) have achieved outstanding performance in many fields, from the automatic translation to speech and image recognition [1, 2].

The design of recommendations strategies in the adaptive learning system focuses on utilizing currently available information to provide individual-specific learning instructions for learners. As a critical motivate for human behaviors, curiosity is essentially the drive to explore knowledge and seek information. In a psychologically inspired view, we aim to incorporate the element of curiosity for guiding learners to study spontaneously. In this paper, a curiosity-driven recommendation policy is proposed under the reinforcement learning framework, allowing for a both efficient and enjoyable personalized learning mode. Given intrinsic rewards from a well-designed predictive model, we apply the actor-critic method to approximate the policy directly through neural networks. Numeric analyses with a large continuous knowledge state space and concrete learning scenarios are used to further demonstrate the power of the proposed method.

In this paper, we introduce a new gait segmentation method based on accelerometer data and develop a new distance function between two time series, showing novel and effectiveness in simultaneously identifying user and adversary. Comparing with the normally used Neural Network methods, our approaches use geometric features to extract walking cycles more precisely and employ a new similarity metric to conduct user-adversary identification. This new technology for simultaneously identify user and adversary contributes to cybersecurity beyond user-only identification. In particular, the new technology is being applied to cell phone recorded walking data and performs an accuracy of $98.79\%$ for 6 classes classification (user-adversary identification) and $99.06\%$ for binary classification (user only identification). In addition to walking signal, our approach works on walking up, walking down and mixed walking signals. This technology is feasible for both large and small data set, overcoming the current challenges facing to Neural Networks such as tuning large number of hyper-parameters for large data sets and lacking of training data for small data sets. In addition, the new distance function developed here can be applied in any signal analysis.

We consider first order expansions of convex penalized estimators in high-dimensional regression problems with random designs. Our setting includes linear regression and logistic regression as special cases. For a given penalty function $h$ and the corresponding penalized estimator $\hat\beta$, we construct a quantity $\eta$, the first order expansion of $\hat\beta$, such that the distance between $\hat\beta$ and $\eta$ is an order of magnitude smaller than the estimation error $\|\hat{\beta} - \beta^*\|$. In this sense, the first order expansion $\eta$ can be thought of as a generalization of influence functions from the mathematical statistics literature to regularized estimators in high-dimensions. Such first order expansion implies that the risk of $\hat{\beta}$ is asymptotically the same as the risk of $\eta$ which leads to a precise characterization of the MSE of $\hat\beta$; this characterization takes a particularly simple form for isotropic design. Such first order expansion also leads to inference results based on $\hat{\beta}$. We provide sufficient conditions for the existence of such first order expansion for three regularizers: the Lasso in its constrained form, the lasso in its penalized form, and the Group-Lasso. The results apply to general loss functions under some conditions and those conditions are satisfied for the squared loss in linear regression and for the logistic loss in the logistic model.

Predicting human behavior is a difficult and crucial task required for motion planning. It is challenging in large part due to the highly uncertain and multi-modal set of possible outcomes in real-world domains such as autonomous driving. Beyond single MAP trajectory prediction, obtaining an accurate probability distribution of the future is an area of active interest. We present MultiPath, which leverages a fixed set of future state-sequence anchors that correspond to modes of the trajectory distribution. At inference, our model predicts a discrete distribution over the anchors and, for each anchor, regresses offsets from anchor waypoints along with uncertainties, yielding a Gaussian mixture at each time step. Our model is efficient, requiring only one forward inference pass to obtain multi-modal future distributions, and the output is parametric, allowing compact communication and analytical probabilistic queries. We show on several datasets that our model achieves more accurate predictions, and compared to sampling baselines, does so with an order of magnitude fewer trajectories.

In the domain of machine learning, Neural Memory Networks (NMNs) have recently achieved impressive results in a variety of application areas including visual question answering, trajectory prediction, object tracking, and language modelling. However, we observe that the attention based knowledge retrieval mechanisms used in current NMNs restricts them from achieving their full potential as the attention process retrieves information based on a set of static connection weights. This is suboptimal in a setting where there are vast differences among samples in the data domain; such as anomaly detection where there is no consistent criteria for what constitutes an anomaly. In this paper, we propose a plastic neural memory access mechanism which exploits both static and dynamic connection weights in the memory read, write and output generation procedures. We demonstrate the effectiveness and flexibility of the proposed memory model in three challenging anomaly detection tasks in the medical domain: abnormal EEG identification, MRI tumour type classification and schizophrenia risk detection in children. In all settings, the proposed approach outperforms the current state-of-the-art. Furthermore, we perform an in-depth analysis demonstrating the utility of neural plasticity for the knowledge retrieval process and provide evidence on how the proposed memory model generates sparse yet informative memory outputs.

Selecting an optimizer is a central step in the contemporary deep learning pipeline. In this paper, we demonstrate the sensitivity of optimizer comparisons to the metaparameter tuning protocol. Our findings suggest that the metaparameter search space may be the single most important factor explaining the rankings obtained by recent empirical comparisons in the literature. In fact, we show that these results can be contradicted when metaparameter search spaces are changed. As tuning effort grows without bound, more general optimizers should never underperform the ones they can approximate (i.e., Adam should never perform worse than momentum), but recent attempts to compare optimizers either assume these inclusion relationships are not practically relevant or restrict the metaparameters in ways that break the inclusions. In our experiments, we find that inclusion relationships between optimizers matter in practice and always predict optimizer comparisons. In particular, we find that the popular adaptive gradient methods never underperform momentum or gradient descent. We also report practical tips around tuning often ignored metaparameters of adaptive gradient methods and raise concerns about fairly benchmarking optimizers for neural network training.

We present a new method which generalizes subspace learning based on eigenvalue and generalized eigenvalue problems. This method, Roweis Discriminant Analysis (RDA), is named after Sam Roweis to whom the field of subspace learning owes significantly. RDA is a family of infinite number of algorithms where Principal Component Analysis (PCA), Supervised PCA (SPCA), and Fisher Discriminant Analysis (FDA) are special cases. One of the extreme special cases, which we name Double Supervised Discriminant Analysis (DSDA), uses the labels twice; it is novel and has not appeared elsewhere. We propose a dual for RDA for some special cases. We also propose kernel RDA, generalizing kernel PCA, kernel SPCA, and kernel FDA, using both dual RDA and representation theory. Our theoretical analysis explains previously known facts such as why SPCA can use regression but FDA cannot, why PCA and SPCA have duals but FDA does not, why kernel PCA and kernel SPCA use kernel trick but kernel FDA does not, and why PCA is the best linear method for reconstruction. Roweisfaces and kernel Roweisfaces are also proposed generalizing eigenfaces, Fisherfaces, supervised eigenfaces, and their kernel variants. We also report experiments showing the effectiveness of RDA and kernel RDA on some benchmark datasets.