The rise of machine-learning systems that process sensory input has brought with it a rise in comparisons between human and machine perception. But such comparisons face a challenge: Whereas machine perception of some stimulus can often be probed through direct and explicit measures, much of human perceptual knowledge is latent, incomplete, or unavailable for explicit report. Here, we explore how this asymmetry can cause such comparisons to misestimate the overlap in human and machine perception. As a case study, we consider human perception of \textit{adversarial speech} -- synthetic audio commands that are recognized as valid messages by automated speech-recognition systems but that human listeners reportedly hear as meaningless noise. In five experiments, we adapt task designs from the human psychophysics literature to show that even when subjects cannot freely transcribe such speech commands (the previous benchmark for human understanding), they often can demonstrate other forms of understanding, including discriminating adversarial speech from closely matched non-speech (Experiments 1--2), finishing common phrases begun in adversarial speech (Experiments 3--4), and solving simple math problems posed in adversarial speech (Experiment 5) -- even for stimuli previously described as unintelligible to human listeners. We recommend the adoption of such "sensitive tests" when comparing human and machine perception, and we discuss the broader consequences of such approaches for assessing the overlap between systems.
Information is frequently retrieved from valid personal ID cards by the authorised organisation to address different purposes. The successful information retrieval (IR) depends on the accuracy and timing process. A process which necessitates a long time to respond is frustrating for both sides in the exchange of data. This paper aims to propose a series of state-of-the-art methods for the journey of an Identification card (ID) from the scanning or capture phase to the point before Optical character recognition (OCR). The key factors for this proposal are the accuracy and speed of the process during the journey. The experimental results of this research prove that utilising the methods based on deep learning, such as Efficient and Accurate Scene Text (EAST) detector and Deep Neural Network (DNN) for face detection, instead of traditional methods increase the efficiency considerably.
Given a causal graph, the do-calculus can express treatment effects as functionals of the observational joint distribution that can be estimated empirically. Sometimes the do-calculus identifies multiple valid formulae, prompting us to compare the statistical properties of the corresponding estimators. For example, the backdoor formula applies when all confounders are observed and the frontdoor formula applies when an observed mediator transmits the causal effect. In this paper, we investigate the over-identified scenario where both confounders and mediators are observed, rendering both estimators valid. Addressing the linear Gaussian causal model, we demonstrate that either estimator can dominate the other by an unbounded constant factor. Next, we derive an optimal estimator, which leverages all observed variables, and bound its finite-sample variance. We show that it strictly outperforms the backdoor and frontdoor estimators and that this improvement can be unbounded. We also present a procedure for combining two datasets, one with observed confounders and another with observed mediators. Finally, we evaluate our methods on both simulated data and the IHDP and JTPA datasets.
Graph matching (GM), as a longstanding problem in computer vision and pattern recognition, still suffers from numerous cluttered outliers in practical applications. To address this issue, we present the zero-assignment constraint (ZAC) for approaching the graph matching problem in the presence of outliers. The underlying idea is to suppress the matchings of outliers by assigning zero-valued vectors to the potential outliers in the obtained optimal correspondence matrix. We provide elaborate theoretical analysis to the problem, i.e., GM with ZAC, and figure out that the GM problem with and without outliers are intrinsically different, which enables us to put forward a sufficient condition to construct valid and reasonable objective function. Consequently, we design an efficient outlier-robust algorithm to significantly reduce the incorrect or redundant matchings caused by numerous outliers. Extensive experiments demonstrate that our method can achieve the state-of-the-art performance in terms of accuracy and efficiency, especially in the presence of numerous outliers.
Interventions are of fundamental importance in Pearl's probabilistic causality regime. In this paper, we will inspect how interventions influence the interpretation of causation in causal models in specific situation. To this end, we will introduce a priori relationships as non-causal relationships in a causal system. Then, we will proceed to discuss the cases that interventions can lead to spurious causation interpretations. This includes the interventional detection of a priori relationships, and cases where the interventional detection of causality forms structural causal models that are not valid in natural situations. We will also discuss other properties of a priori relations and SCMs that have a priori information in their structural equations.
With an exponential explosive growth of various digital text information, it is challenging to efficiently obtain specific knowledge from massive unstructured text information. As one basic task for natural language processing (NLP), relation extraction aims to extract the semantic relation between entity pairs based on the given text. To avoid manual labeling of datasets, distant supervision relation extraction (DSRE) has been widely used, aiming to utilize knowledge base to automatically annotate datasets. Unfortunately, this method heavily suffers from wrong labelling due to the underlying strong assumptions. To address this issue, we propose a new framework using hybrid attention-based Transformer block with multi-instance learning to perform the DSRE task. More specifically, the Transformer block is firstly used as the sentence encoder to capture syntactic information of sentences, which mainly utilizes multi-head self-attention to extract features from word level. Then, a more concise sentence-level attention mechanism is adopted to constitute the bag representation, aiming to incorporate valid information of each sentence to effectively represent the bag. Experimental results on the public dataset New York Times (NYT) demonstrate that the proposed approach can outperform the state-of-the-art algorithms on the evaluation dataset, which verifies the effectiveness of our model for the DSRE task.
Identifying a patient's key problems over time is a common task for providers at the point care, yet a complex and time-consuming activity given current electric health records. To enable a problem-oriented summarizer to identify a patient's comprehensive list of problems and their salience, we propose an unsupervised phenotyping approach that jointly learns a large number of phenotypes/problems across structured and unstructured data. To identify the appropriate granularity of the learned phenotypes, the model is trained on a target patient population of the same clinic. To enable the content organization of a problem-oriented summarizer, the model identifies phenotype relatedness as well. The model leverages a correlated-mixed membership approach with variational inference applied to heterogenous clinical data. In this paper, we focus our experiments on assessing the learned phenotypes and their relatedness as learned from a specific patient population. We ground our experiments in phenotyping patients from an HIV clinic in a large urban care institution (n=7,523), where patients have voluminous, longitudinal documentation, and where providers would benefit from summaries of these patient's medical histories, whether about their HIV or any comorbidities. We find that the learned phenotypes and their relatedness are clinically valid when assessed qualitatively by clinical experts, and that the model surpasses baseline in inferring phenotype-relatedness when comparing to existing expert-curated condition groupings.
Design-consistent model-assisted estimation has become the standard practice in survey sampling. However, a general theory is lacking so far, which allows one to incorporate modern machine-learning techniques that can lead to potentially much more powerful assisting models. We propose a subsampling Rao-Blackwell method, and develop a statistical learning theory for exactly design-unbiased estimation with the help of linear or non-linear prediction models. Our approach makes use of classic ideas from Statistical Science as well as the rapidly growing field of Machine Learning. Provided rich auxiliary information, it can yield considerable efficiency gains over standard linear model-assisted methods, while ensuring valid estimation for the given target population, which is robust against potential mis-specifications of the assisting model at the individual level.
We detail an approach to develop Stein's method for bounding integral metrics on probability measures defined on a Riemannian manifold $\mathbf M$. Our approach exploits the relationship between the generator of a diffusion on $\mathbf M$ with target invariant measure and its characterising Stein operator. We consider a pair of such diffusions with different starting points, and through analysis of the distance process between the pair, derive Stein factors, which bound the solution to the Stein equation and its derivatives. The Stein factors contain curvature-dependent terms and reduce to those currently available for $\mathbb R^m$, and moreover imply that the bounds for $\mathbb R^m$ remain valid when $\mathbf M$ is a flat manifold
Image classifiers are typically scored on their test set accuracy, but high accuracy can mask a subtle type of model failure. We find that high scoring convolutional neural networks (CNNs) on popular benchmarks exhibit troubling pathologies that allow them to display high accuracy even in the absence of semantically salient features. When a model provides a high-confidence decision without salient supporting input features, we say the classifier has overinterpreted its input, finding too much class-evidence in patterns that appear nonsensical to humans. Here, we demonstrate that neural networks trained on CIFAR-10 and ImageNet suffer from overinterpretation, and we find models on CIFAR-10 make confident predictions even when 95% of input images are masked and humans cannot discern salient features in the remaining pixel-subsets. We introduce Batched Gradient SIS, a new method for discovering sufficient input subsets for complex datasets, and use this method to show the sufficiency of border pixels in ImageNet for training and testing. Although these patterns portend potential model fragility in real-world deployment, they are in fact valid statistical patterns of the benchmark that alone suffice to attain high test accuracy. Unlike adversarial examples, overinterpretation relies upon unmodified image pixels. We find ensembling and input dropout can each help mitigate overinterpretation.
Data-driven sequential decision has found a wide range of applications in modern operations management, such as dynamic pricing, inventory control, and assortment optimization. Most existing research on data-driven sequential decision focuses on designing an online policy to maximize the revenue. However, the research on uncertainty quantification on the underlying true model function (e.g., demand function), a critical problem for practitioners, has not been well explored. In this paper, using the problem of demand function prediction in dynamic pricing as the motivating example, we study the problem of constructing accurate confidence intervals for the demand function. The main challenge is that sequentially collected data leads to significant distributional bias in the maximum likelihood estimator or the empirical risk minimization estimate, making classical statistics approaches such as the Wald's test no longer valid. We address this challenge by developing a debiased approach and provide the asymptotic normality guarantee of the debiased estimator. Based this the debiased estimator, we provide both point-wise and uniform confidence intervals of the demand function.
Natural environment and our interaction with it is essentially multisensory, where we may deploy visual, tactile and/or auditory senses to perceive, learn and interact with our environment. Our objective in this study is to develop a scene analysis algorithm using multisensory information, specifically vision and audio. We develop a proto-object based audiovisual saliency map (AVSM) for the analysis of dynamic natural scenes. A specialized audiovisual camera with $360 \degree$ Field of View, capable of locating sound direction, is used to collect spatiotemporally aligned audiovisual data. We demonstrate that the performance of proto-object based audiovisual saliency map in detecting and localizing salient objects/events is in agreement with human judgment. In addition, the proto-object based AVSM that we compute as a linear combination of visual and auditory feature conspicuity maps captures a higher number of valid salient events compared to unisensory saliency maps. Such an algorithm can be useful in surveillance, robotic navigation, video compression and related applications.
A data set was recorded to evaluate different methods for extracting mathematical models for a three-phase permanent magnet synchronous motor (PMSM) and a two-level IGBT inverter from measurement data. It consists of approximately 40 million multidimensional samples from a defined operating range of the drive. This document describes how to use the published data set \cite{Dataset} and how to extract models using introductory examples. The examples are based on known ordinary differential equations, the least squares method or on (deep) machine learning methods. The extracted models are used for the prediction of system states in a model predictive control (MPC) environment of the drive. In case of model deviations, the performance utilizing MPC remains below its potential. This is the case for state-of-the-art white-box models that are based only on nominal drive parameters and are valid in only limited operation regions. Moreover, many parasitic effects (e.g. from the feeding inverter) are normally not covered in white-box models. In order to achieve a high control performance, it is necessary to use models that cover the motor behavior in all operating points sufficiently well.
Image interpolation is a special case of image super-resolution, where the low-resolution image is directly down-sampled from its high-resolution counterpart without blurring and noise. Therefore, assumptions adopted in super-resolution models are not valid for image interpolation. To address this problem, we propose a novel image interpolation model based on sparse representation. Two widely used priors including sparsity and nonlocal self-similarity are used as the regularization terms to enhance the stability of interpolation model. Meanwhile, we incorporate the nonlocal linear regression into this model since nonlocal similar patches could provide a better approximation to a given patch. Moreover, we propose a new approach to learn adaptive sub-dictionary online instead of clustering. For each patch, similar patches are grouped to learn adaptive sub-dictionary, generating a more sparse and accurate representation. Finally, the weighted encoding is introduced to suppress tailing of fitting residuals in data fidelity. Abundant experimental results demonstrate that our proposed method outperforms several state-of-the-art methods in terms of quantitative measures and visual quality.
Dynamic System Identification approaches usually heavily rely on the evolutionary and gradient-based optimisation techniques to produce optimal excitation trajectories for determining the physical parameters of robot platforms. Current optimisation techniques tend to generate single trajectories. This is expensive, and intractable for longer trajectories, thus limiting their efficacy for system identification. We propose to tackle this issue by using multiple shorter cyclic trajectories, which can be generated in parallel, and subsequently combined together to achieve the same effect as a longer trajectory. Crucially, we show how to scale this approach even further by increasing the generation speed and quality of the dataset through the use of generative adversarial network (GAN) based architectures to produce a large databases of valid and diverse excitation trajectories. To the best of our knowledge, this is the first robotics work to explore system identification with multiple cyclic trajectories and to develop GAN-based techniques for scaleably producing excitation trajectories that are diverse in both control parameter and inertial parameter spaces. We show that our approach dramatically accelerates trajectory optimisation, while simultaneously providing more accurate system identification than the conventional approach.
With ever increasing data rates produced by modern radio telescopes like LOFAR and future telescopes like the SKA, many data processing steps are overwhelmed by the amount of data that needs to be handled using limited compute resources. Calibration is one such operation that dominates the overall data processing computational cost, nonetheless, it is an essential operation to reach many science goals. Calibration algorithms do exist that scale well with the number of stations of an array and the number of directions being calibrated. However, the remaining bottleneck is the raw data volume, which scales with the number of baselines, and which is proportional to the square of the number of stations. We propose a 'stochastic' calibration strategy where we only read in a mini-batch of data for obtaining calibration solutions, as opposed to reading the full batch of data being calibrated. Nonetheless, we obtain solutions that are valid for the full batch of data. Normally, data need to be averaged before calibration is performed to accommodate the data in size-limited compute memory. Stochastic calibration overcomes the need for data averaging before any calibration can be performed, and offers many advantages including: enabling the mitigation of faint radio frequency interference; better removal of strong celestial sources from the data; and better detection and spatial localization of fast radio transients.
Consider the online testing of a stream of hypotheses where a real--time decision must be made before the next data point arrives. The error rate is required to be controlled at {all} decision points. Conventional \emph{simultaneous testing rules} are no longer applicable due to the more stringent error constraints and absence of future data. Moreover, the online decision--making process may come to a halt when the total error budget, or alpha--wealth, is exhausted. This work develops a new class of structure--adaptive sequential testing (SAST) rules for online false discover rate (FDR) control. A key element in our proposal is a new alpha--investment algorithm that precisely characterizes the gains and losses in sequential decision making. SAST captures time varying structures of the data stream, learns the optimal threshold adaptively in an ongoing manner and optimizes the alpha-wealth allocation across different time periods. We present theory and numerical results to show that the proposed method is valid for online FDR control and achieves substantial power gain over existing online testing rules.
This paper presents a new approach to 3D object detection that leverages the properties of the data obtained by a LiDAR sensor. State-of-the-art detectors use neural network architectures based on assumptions valid for camera images. However, point clouds obtained from LiDAR are fundamentally different. Most detectors use shared filter kernels to extract features which do not take into account the range dependent nature of the point cloud features. To show this, different detectors are trained on two splits of the KITTI dataset: close range (objects up to 25 meters from LiDAR) and long-range. Top view images are generated from point clouds as input for the networks. Combined results outperform the baseline network trained on the full dataset with a single backbone. Additional research compares the effect of using different input features when converting the point cloud to image. The results indicate that the network focuses on the shape and structure of the objects, rather than exact values of the input. This work proposes an improvement for 3D object detectors by taking into account the properties of LiDAR point clouds over distance. Results show that training separate networks for close-range and long-range objects boosts performance for all KITTI benchmark difficulties.
Deep learning methods continue to have a decided impact on machine learning, both in theory and in practice. Statistical theoretical developments have been mostly concerned with approximability or rates of estimation when recovering infinite dimensional objects (curves or densities). Despite the impressive array of available theoretical results, the literature has been largely silent about uncertainty quantification for deep learning. This paper takes a step forward in this important direction by taking a Bayesian point of view. We study Gaussian approximability of certain aspects of posterior distributions of sparse deep ReLU architectures in non-parametric regression. Building on tools from Bayesian non-parametrics, we provide semi-parametric Bernstein-von Mises theorems for linear and quadratic functionals, which guarantee that implied Bayesian credible regions have valid frequentist coverage. Our results provide new theoretical justifications for (Bayesian) deep learning with ReLU activation functions, highlighting their inferential potential.
Slow motion videos are becoming increasingly popular, but capturing high-resolution videos at extremely high frame rates requires professional high-speed cameras. To mitigate this problem, current techniques increase the frame rate of standard videos through frame interpolation by assuming linear object motion which is not valid in challenging cases. In this paper, we address this problem using two video streams as input; an auxiliary video with high frame rate and low spatial resolution, providing temporal information, in addition to the standard main video with low frame rate and high spatial resolution. We propose a two-stage deep learning system consisting of alignment and appearance estimation that reconstructs high resolution slow motion video from the hybrid video input. For alignment, we propose to compute flows between the missing frame and two existing frames of the main video by utilizing the content of the auxiliary video frames. For appearance estimation, we propose to combine the warped and auxiliary frames using a context and occlusion aware network. We train our model on synthetically generated hybrid videos and show high-quality results on a variety of test scenes. To demonstrate practicality, we show the performance of our system on two real dual camera setups with small baseline.