We investigate online nonlinear regression with long short term memory (LSTM) based networks, which we refer to as LSTM-based online learning. For LSTM-based online learning, we introduce a highly efficient extended Kalman filter (EKF) based training algorithm with a theoretical convergence guarantee. Through simulations, we illustrate significant performance improvements achieved by our algorithm with respect to the conventional LSTM training methods. We particularly show that our algorithm provides very similar error performance with the EKF learning algorithm in 25-40 times shorter training time depending on the parameter size of the network.

Within the last decade, neural network based predictors have demonstrated impressive - and at times super-human - capabilities. This performance is often paid for with an intransparent prediction process and thus has sparked numerous contributions in the novel field of explainable artificial intelligence (XAI). In this paper, we focus on a popular and widely used method of XAI, the Layer-wise Relevance Propagation (LRP). Since its initial proposition LRP has evolved as a method, and a best practice for applying the method has tacitly emerged, based on humanly observed evidence. We investigate - and for the first time quantify - the effect of this current best practice on feedforward neural networks in a visual object detection setting. The results verify that the current, layer-dependent approach to LRP applied in recent literature better represents the model's reasoning, and at the same time increases the object localization and class discriminativity of LRP.

A BSTRACT Since deep neural networks are over-parametrized, they may memorize noisy examples. We address such memorizing issue under the existence of annotation noise. From the fact that deep neural networks cannot generalize neighborhoods of the features acquired via memorization, we find that noisy examples do not consistently incur small losses on the network in the presence of perturbation. Based on this, we propose a novel training method called Learning with Ensemble Consensus (LEC) whose goal is to prevent overfitting noisy examples by eliminating them identified via consensus of an ensemble of perturbed networks. One of the proposed LECs, L TEC outperforms the current state-of-the-art methods on MNIST, CIFAR-10, and CIFAR-100 despite its efficient memory usage. 1 I NTRODUCTION Deep neural networks (DNNs) have shown excellent performance (Krizhevsky et al., 2012; He et al., 2016) on visual recognition datasets (Deng et al., 2009). However, it is difficult to obtain annotated datasets of such high quality in practice (Wang et al., 2018a). Even worse, DNNs may not generalize training data in the presence of noisy examples (Zhang et al., 2016). Therefore, there is an increasing demand for robust training methods. In general, DNNs trained on noisy datasets first generalize clean examples (Arpit et al., 2017).

In this chapter we take a look at the universal approximation question for stochastic feedforward neural networks. In contrast to deterministic networks, which represent mappings from a set of inputs to a set of outputs, stochastic networks represent mappings from a set of inputs to a set of probability distributions over the set of outputs. In particular, even if the sets of inputs and outputs are finite, the class of stochastic mappings in question is not finite. Moreover, while for a deterministic function the values of all output variables can be computed independently of each other given the values of the inputs, in the stochastic setting the values of the output variables may need to be correlated, which requires that their values are computed jointly. A prominent class of stochastic feedforward networks which has played a key role in the resurgence of deep learning are deep belief networks. The representational power of these networks has been studied mainly in the generative setting, as models of probability distributions without an input, or in the discriminative setting for the special case of deterministic mappings. We study the representational power of deep sigmoid belief networks in terms of compositions of linear transformations of probability distributions, Markov kernels, that can be expressed by the layers of the network. We investigate different types of shallow and deep architectures, and the minimal number of layers and units per layer that are sufficient and necessary in order for the network to be able to approximate any given stochastic mapping from the set of inputs to the set of outputs arbitrarily well.

The aim of clinical effectiveness research using repositories of electronic health records is to identify what health interventions 'work best' in real-world settings. Since there are several reasons why the net benefit of intervention may differ across patients, current comparative effectiveness literature focuses on investigating heterogeneous treatment effect and predicting whether an individual might benefit from an intervention. The majority of this literature has concentrated on the estimation of the effect of treatment on binary outcomes. However, many medical interventions are evaluated in terms of their effect on future events, which are subject to loss to follow-up. In this study, we describe a framework for the estimation of heterogeneous treatment effect in terms of differences in time-to-event (survival) probabilities. We divide the problem into three phases: (1) estimation of treatment effect conditioned on unique sets of the covariate vector; (2) identification of features important for heterogeneity using an ensemble of non-parametric variable importance methods; and (3) estimation of treatment effect on the reference classes defined by the previously selected features, using one-step Targeted Maximum Likelihood Estimation. We conducted a series of simulation studies and found that this method performs well when either sample size or event rate is high enough and the number of covariates contributing to the effect heterogeneity is moderate. An application of this method to a clinical case study was conducted by estimating the effect of oral anticoagulants on newly diagnosed non-valvular atrial fibrillation patients using data from the UK Clinical Practice Research Datalink.

Graph Convolutional Network (GCN) has attracted intensive interests recently. One major limitation of GCN is that it often cannot benefit from using a deep architecture, while traditional CNN and an alternative Graph Neural Network architecture, namely GraphCNN, often achieve better quality with a deeper neural architecture. How can we explain this phenomenon? In this paper, we take the first step towards answering this question. We first conduct a systematic empirical study on the accuracy of GCN, GraphCNN, and ResNet-18 on 2D images and identified relative importance of different factors in architectural design. This inspired a novel theoretical analysis on the mutual information between the input and the output after l GCN/ GraphCNN layers. We identified regimes in which GCN suffers exponentially fast "information lose" and show that GraphCNN requires a much weaker condition for similar behavior to happen. Extending convolutional neural networks (CNN) over images to a graph has attracted intense interest recently. One early attempt is the GCN model proposed by Kipf & Welling (2016a). However, when applying GCN to many practical applications, one discrepancy lingers -- although traditional CNN usually gets higher accuracy when it goes deeper, GCN, as a natural extension of CNN, does not seem to benefit much from going deeper by stacking multiple layers together. This phenomenon has been the focus of multiple recent papers (Li et al., 2018; 2019; Oono & Suzuki, 2019). On the theoretical side, Li et al. (2018) and Oono & Suzuki (2019) identified the problem as oversmoothing -- under certain conditions, when multiple GCN layers are stacked together, the output will converge to a region that is independent of weights and inputs. On the empirical side, Li et al. (2019) showed that many techniques that were designed to train a deep CNN, e.g., the skip connections in ResNet (He et al., 2016a), can also make it easier for GCN to go deeper.

Suicide is a critical issue in the modern society. Early detection and prevention of suicide attempt should be addressed to save people's life. Current suicidal ideation detection methods include clinical methods based on the interaction between social workers or experts and the targeted individuals, and machine learning techniques with feature engineering or deep learning for automatic detection based on online social contents. This is the first survey that comprehensively introduces and discusses the methods from these categories. Domain-specific applications of suicidal ideation detection are also reviewed according to their data sources, i.e., questionnaires, electronic health records, suicide notes, and online user content. To facilitate further research, several specific tasks and datasets are introduced. Finally, we summarize the limitations of current work and provide an outlook of further research directions.

Despite of the recent progress in agents that learn through interaction, there are several challenges in terms of sample efficiency and generalization across unseen behaviors during training. To mitigate these problems, we propose and apply a first-order Meta-Learning algorithm called Bottom-Up Meta-Policy Search (BUMPS), which works with two-phase optimization procedure: firstly, in a meta-training phase, it distills few expert policies to create a meta-policy capable of generalizing knowledge to unseen tasks during training; secondly, it applies a fast adaptation strategy named Policy Filtering, which evaluates few policies sampled from the meta-policy distribution and selects which best solves the task. We conducted all experiments in the RoboCup 3D Soccer Simulation domain, in the context of kick motion learning. We show that, given our experimental setup, BUMPS works in scenarios where simple multi-task Reinforcement Learning does not. Finally, we performed experiments in a way to evaluate each component of the algorithm.

In the last years, Artificial Intelligence (AI) has achieved a notable momentum that may deliver the best of expectations over many application sectors across the field. For this to occur, the entire community stands in front of the barrier of explainability, an inherent problem of AI techniques brought by sub-symbolism (e.g. ensembles or Deep Neural Networks) that were not present in the last hype of AI. Paradigms underlying this problem fall within the so-called eXplainable AI (XAI) field, which is acknowledged as a crucial feature for the practical deployment of AI models. This overview examines the existing literature in the field of XAI, including a prospect toward what is yet to be reached. We summarize previous efforts to define explainability in Machine Learning, establishing a novel definition that covers prior conceptual propositions with a major focus on the audience for which explainability is sought. We then propose and discuss about a taxonomy of recent contributions related to the explainability of different Machine Learning models, including those aimed at Deep Learning methods for which a second taxonomy is built. This literature analysis serves as the background for a series of challenges faced by XAI, such as the crossroads between data fusion and explainability. Our prospects lead toward the concept of Responsible Artificial Intelligence, namely, a methodology for the large-scale implementation of AI methods in real organizations with fairness, model explainability and accountability at its core. Our ultimate goal is to provide newcomers to XAI with a reference material in order to stimulate future research advances, but also to encourage experts and professionals from other disciplines to embrace the benefits of AI in their activity sectors, without any prior bias for its lack of interpretability.

A BSTRACT Increasing model size when pretraining natural language representations often results in improved performance on downstream tasks. However, at some point further model increases become harder due to GPU/TPU memory limitations, longer training times, and unexpected model degradation. To address these problems, we present two parameter-reduction techniques to lower memory consumption and increase the training speed of BERT (Devlin et al., 2019). Comprehensive empirical evidence shows that our proposed methods lead to models that scale much better compared to the original BERT. We also use a self-supervised loss that focuses on modeling inter-sentence coherence, and show it consistently helps downstream tasks with multi-sentence inputs. As a result, our best model establishes new state-of-the-art results on the GLUE, RACE, and SQuAD benchmarks while having fewer parameters compared to BERT -large. The code and the pretrained models are available at https://github.com/ Many nontrivial NLP tasks, including those that have limited training data, have greatly benefited from these pre-trained models. One of the most compelling signs of these breakthroughs is the evolution of machine performance on a reading comprehension task designed for middle and highschool English exams in China, the RACE test (Lai et al., 2017): the paper that originally describes the task and formulates the modeling challenge reports then state-of-the-art machine accuracy at 44. 1%; the latest published result reports their model performance at 83. 2% (Liu et al., 2019); the work we present here pushes it even higher to 89 .4%, a stunning 45 .3% Evidence from these improvements reveals that a large network is of crucial importance for achieving state-of-the-art performance (Devlin et al., 2019; Radford et al., 2019). It has become common practice to pre-train large models and distill them down to smaller ones (Sun et al., 2019; Turc et al., 2019) for real applications.