Recent efforts to improve the interpretability of deep neural networks use saliency to characterize the importance of input features to predictions made by models. Work on interpretability using saliency-based methods on Recurrent Neural Networks (RNNs) has mostly targeted language tasks, and their applicability to time series data is less understood. In this work we analyze saliency-based methods for RNNs, both classical and gated cell architectures. We show that RNN saliency vanishes over time, biasing detection of salient features only to later time steps and are, therefore, incapable of reliably detecting important features at arbitrary time intervals. To address this vanishing saliency problem, we propose a novel RNN cell structure (input-cell attention), which can extend any RNN cell architecture.

Bayesian methods promise to fix many shortcomings of deep learning, but they are impractical and rarely match the performance of standard methods, let alone improve them. In this paper, we demonstrate practical training of deep networks with natural-gradient variational inference. By applying techniques such as batch normalisation, data augmentation, and distributed training, we achieve similar performance in about the same number of epochs as the Adam optimiser, even on large datasets such as ImageNet. Importantly, the benefits of Bayesian principles are preserved: predictive probabilities are well-calibrated, uncertainties on out-of-distribution data are improved, and continual-learning performance is boosted. This work enables practical deep learning while preserving benefits of Bayesian principles.

Deep neural networks (DNN) and Gaussian processes (GP) are two powerful models with several theoretical connections relating them, but the relationship between their training methods is not well understood. In this paper, we show that certain Gaussian posterior approximations for Bayesian DNNs are equivalent to GP posteriors. This enables us to relate solutions and iterations of a deep-learning algorithm to GP inference. As a result, we can obtain a GP kernel and a nonlinear feature map while training a DNN. Surprisingly, the resulting kernel is the neural tangent kernel. We show kernels obtained on real datasets and demonstrate the use of the GP marginal likelihood to tune hyperparameters of DNNs. Our work aims to facilitate further research on combining DNNs and GPs in practical settings.

Deep Neural Networks (DNNs) have been criticized because they easily overfit noisy (incorrect) labels. To improve the robustness of DNNs, existing methods for image data regard samples with small training losses as correctly labeled data (small-loss criterion). Nevertheless, time series' discriminative patterns are easily distorted by external noises (i.e., frequency perturbations) during the recording process. This results in training losses of some time series samples that do not meet the small-loss criterion. Therefore, this paper proposes a deep learning paradigm called Scale-teaching to cope with time series noisy labels. Specifically, we design a fine-to-coarse cross-scale fusion mechanism for learning discriminative patterns by utilizing time series at different scales to train multiple DNNs simultaneously. Meanwhile, each network is trained in a cross-teaching manner by using complementary information from different scales to select small-loss samples as clean labels. For unselected large-loss samples, we introduce multi-scale embedding graph learning via label propagation to correct their labels by using selected clean samples. Experiments on multiple benchmark time series datasets demonstrate the superiority of the proposed Scale-teaching paradigm over state-of-the-art methods in terms of effectiveness and robustness.

Many attempts have been done to extend the great success of convolutional neural networks (CNNs) achieved on high-end GPU servers to portable devices such as smart phones. Providing compression and acceleration service of deep learning models on the cloud is therefore of significance and is attractive for end users.

Wind energy resource quantification, air pollution monitoring, and weather forecasting all rely on rapid, accurate measurement of local wind conditions. Visual observations of the effects of wind---the swaying of trees and flapping of flags, for example---encode information regarding local wind conditions that can potentially be leveraged for visual anemometry that is inexpensive and ubiquitous. Here, we demonstrate a coupled convolutional neural network and recurrent neural network architecture that extracts the wind speed encoded in visually recorded flow-structure interactions of a flag and tree in naturally occurring wind. Predictions for wind speeds ranging from 0.75-11 m/s showed agreement with measurements from a cup anemometer on site, with a root-mean-squared error approaching the natural wind speed variability due to atmospheric turbulence. Generalizability of the network was demonstrated by successful prediction of wind speed based on recordings of other flags in the field and in a controlled wind tunnel test. Furthermore, physics-based scaling of the flapping dynamics accurately predicts the dependence of the network performance on the video frame rate and duration.

Standard approaches for uncertainty quantification in deep learning and physics-informed learning have persistent limitations. Indicatively, strong assumptions regarding the data likelihood are required, the performance highly depends on the selection of priors, and the posterior can be sampled only approximately, which leads to poor approximations because of the associated computational cost.This paper introduces and studies confidence interval (CI) estimation for deterministic partial differential equations as a novel problem.That is, to propagate confidence, in the form of CIs, from data locations to the entire domain with probabilistic guarantees.We propose a method, termed Physics-Informed Confidence Propagation (PICProp), based on bi-level optimization to compute a valid CI without making heavy assumptions.We provide a theorem regarding the validity of our method, and computational experiments, where the focus is on physics-informed learning.

Knowledge tracing (KT) is a task that predicts students' future performance based on their historical learning interactions. With the rapid development of deep learning techniques, existing KT approaches follow a data-driven paradigm that uses massive problem-solving records to model students' learning processes. However, although the educational contexts contain various factors that may have an influence on student learning outcomes, existing public KT datasets mainly consist of anonymized ID-like features, which may hinder the research advances towards this field. Therefore, in this work, we present, \emph{XES3G5M}, a large-scale dataset with rich auxiliary information about questions and their associated knowledge components (KCs)\footnote{\label{ft:kc}A KC is a generalization of everyday terms like concept, principle, fact, or skill.}. The XES3G5M dataset is collected from a real-world online math learning platform, which contains 7,652 questions, and 865 KCs with 5,549,635 interactions from 18,066 students. To the best of our knowledge, the XES3G5M dataset not only has the largest number of KCs in math domain but contains the richest contextual information including tree structured KC relations, question types, textual contents and analysis and student response timestamps. Furthermore, we build a comprehensive benchmark on 19 state-of-the-art deep learning based knowledge tracing (DLKT) models. Extensive experiments demonstrate the effectiveness of leveraging the auxiliary information in our XES3G5M with DLKT models. We hope the proposed dataset can effectively facilitate the KT research work.

Forecasting complex time series is ubiquitous and vital in a range of applications but challenging. Recent advances endeavor to achieve progress by incorporating various deep learning techniques (e.g., RNN and Transformer) into sequential models. However, clear patterns are still hard to extract since time series are often composed of several intricately entangled components. Motivated by the success of disentangled variational autoencoder in computer vision and classical time series decomposition, we plan to infer a couple of representations that depict seasonal and trend components of time series. To achieve this goal, we propose LaST, which, based on variational inference, aims to disentangle the seasonal-trend representations in the latent space. Furthermore, LaST supervises and disassociates representations from the perspectives of themselves and input reconstruction, and introduces a series of auxiliary objectives. Extensive experiments prove that LaST achieves state-of-the-art performance on time series forecasting task against the most advanced representation learning and end-to-end forecasting models. For reproducibility, our implementation is publicly available on Github.

Normalization methods play an important role in enhancing the performance of deep learning while their theoretical understandings have been limited. To theoretically elucidate the effectiveness of normalization, we quantify the geometry of the parameter space determined by the Fisher information matrix (FIM), which also corresponds to the local shape of the loss landscape under certain conditions. We analyze deep neural networks with random initialization, which is known to suffer from a pathologically sharp shape of the landscape when the network becomes sufficiently wide. We reveal that batch normalization in the last layer contributes to drastically decreasing such pathological sharpness if the width and sample number satisfy a specific condition. In contrast, it is hard for batch normalization in the middle hidden layers to alleviate pathological sharpness in many settings. We also found that layer normalization cannot alleviate pathological sharpness either. Thus, we can conclude that batch normalization in the last layer significantly contributes to decreasing the sharpness induced by the FIM.