• Home
  • James Cameron Bailey
James Cameron Bailey

James Cameron Bailey
Star Valley drilling

About

314
Publications
37,409
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
8,115
Citations

Publications

Publications (314)
Article
Full-text available
Properties of data distributions can be assessed at both global and local scales. At a highly localized scale, a fundamental measure is the local intrinsic dimensionality (LID), which assesses growth rates of the cumulative distribution function within a restricted neighborhood and characterizes properties of the geometry of a local neighborhood. I...
Article
The predict+optimize problem combines machine learning and combinatorial optimization by predicting the problem coefficients first and then using these coefficients to solve the optimization problem. While this problem can be solved in two separate stages, recent research shows end to end models can achieve better results. This requires differentia...
Article
Full-text available
Experiments have long shown that zones of near vanishing deformation, so-called “dead zones”, emerge and coexist with strain localization zones inside deforming granular media. To date, a method that can disentangle these dynamically coupled structures from each other, from pre- to post- failure, is lacking. Here we develop a framework that learns...
Conference Paper
Full-text available
Though recent technological advances have enabled note-taking through different modalities (e.g., keyboard, digital ink, voice), there is still a lack of understanding of the effect of the modality choice on learning. In this paper, we compared two note-taking input modalities—keyboard and voice—to study their effects on participants' learning. We...
Conference Paper
Full-text available
Gaze and speech are rich contextual sources of information that, when combined, can result in effective and rich multimodal interactions. This paper proposes a machine learning-based pipeline that leverages and combines users' natural gaze activity, the semantic knowledge from their vocal utterances and the synchronicity between gaze and speech dat...
Preprint
Full-text available
Improving the robustness of deep neural networks (DNNs) to adversarial examples is an important yet challenging problem for secure deep learning. Across existing defense techniques, adversarial training with Projected Gradient Decent (PGD) is amongst the most effective. Adversarial training solves a min-max optimization problem, with the \textit{in...
Preprint
Full-text available
Bounding box (bbox) regression is a fundamental task in computer vision. So far, the most commonly used loss functions for bbox regression are the Intersection over Union (IoU) loss and its variants. In this paper, we generalize existing IoU-based losses to a new family of power IoU losses that have a power IoU term and an additional power regulari...
Preprint
Full-text available
Deep neural networks (DNNs) are known to be vulnerable to adversarial attacks. A range of defense methods have been proposed to train adversarially robust DNNs, among which adversarial training has demonstrated promising results. However, despite preliminary understandings developed for adversarial training, it is still not clear, from the architec...
Chapter
The local intrinsic dimensionality (LID) model assesses the complexity of data within the vicinity of a query point, through the growth rate of the probability measure within an expanding neighborhood. In this paper, we show how LID is asymptotically related to the entropy of the lower tail of the distribution of distances from the query. We establ...
Conference Paper
Full-text available
Deep neural networks (DNNs) are known to be vulnerable to adversarial examples/attacks, raising concerns about their reliability in safety-critical applications. A number of defense methods have been proposed to train robust DNNs resistant to adversarial attacks, among which adversarial training has so far demonstrated the most promising results. H...
Article
Full-text available
Annotation is an effective reading strategy people often undertake while interacting with digital text. It involves highlighting pieces of text and making notes about them. Annotating while reading in a desktop environment is considered trivial but, in a mobile setting where people read while hand-holding devices, the task of highlighting and typin...
Article
Full-text available
We propose a new metric called s -LID based on the concept of Local Intrinsic Dimensionality to identify and quantify hierarchies of kinematic patterns in heterogeneous media. s -LID measures how outlying a grain’s motion is relative to its s nearest neighbors in displacement state space. To demonstrate the merits of s -LID over the conventional me...
Preprint
Deep neural networks (DNNs) are known to be vulnerable to adversarial examples/attacks, raising concerns about their reliability in safety-critical applications. A number of defense methods have been proposed to train robust DNNs resistant to adversarial attacks, among which adversarial training has so far demonstrated the most promising results. H...
Preprint
Full-text available
We propose a new metric called s-LID based on the concept of Local Intrinsic Dimensionality to identify and quantify hierarchies of kinematic patterns in heterogeneous media. s-LID measures how outlying a grain's motion is relative to its s nearest neighbors in displacement state space. To demonstrate the merits of s-LID over the conventional measu...
Preprint
Annotation is an effective reading strategy people often undertake while interacting with digital text. It involves highlighting pieces of text and making notes about them. Annotating while reading in a desktop environment is considered trivial but, in a mobile setting where people read while hand-holding devices, the task of highlighting and typin...
Article
Full-text available
Task difficulty (TD) reflects students' subjective judgement on the complexity of a task. We examine the TDs data of 236 undergraduate students in a simulation-based Predict-Observe-Explain (POE) environment using three different labels easy, medium and hard. Generally, the students who perceive the tasks to be easy or hard perform poorly at the tr...
Preprint
Full-text available
The volume of "free" data on the internet has been key to the current success of deep learning. However, it also raises privacy concerns about the unauthorized exploitation of personal data for training commercial models. It is thus crucial to develop methods to prevent unauthorized data exploitation. This paper raises the question: \emph{can data...
Preprint
Full-text available
Neural Architecture Search (NAS) has gained significant popularity as an effective tool for designing high performance deep neural networks (DNNs). NAS can be performed via policy gradient, evolutionary algorithms, differentiable architecture search or tree-search methods. While significant progress has been made for both policy gradient and differ...
Article
Full-text available
Confusion is an important epistemic emotion because it can help students focus their attention and effort when solving complex learning tasks. However, unresolved confusion can be detrimental because it may result in students’ disengagement. This is especially concerning in simulation environments using discovery-based learning, which puts more of...
Preprint
Though recent technological advances have enabled note-taking through different modalities (e.g., keyboard, digital ink, voice), there is still a lack of understanding of the effect of the modality choice on learning. In this paper, we compared two note-taking input modalities -- keyboard and voice -- to study their effects on participants' learnin...
Preprint
Full-text available
The predict+optimize problem combines machine learning ofproblem coefficients with a combinatorial optimization prob-lem that uses the predicted coefficients. While this problemcan be solved in two separate stages, it is better to directlyminimize the optimization loss. However, this requires dif-ferentiating through a discrete, non-differentiable...
Chapter
Recent studies have shown that DNNs can be compromised by backdoor attacks crafted at training time. A backdoor attack installs a backdoor into the victim model by injecting a backdoor pattern into a small proportion of the training data. At test time, the victim model behaves normally on clean test data, yet consistently predicts a specific (likel...
Preprint
Full-text available
Task difficulty (TD) reflects students' subjective judgement on the complexity of a task. We examine the TDs data of 236 undergraduate students in a simulation-based Predict-Observe-Explain (POE) environment using three different labels easy, medium and hard. Generally, the students who perceive the tasks to be easy or hard perform poorly at the tr...
Article
Machine learning systems are vulnerable to adversarial attack. By applying to the input object a small, carefully-designed perturbation, a classifier can be tricked into making an incorrect prediction. This phenomenon has drawn wide interest, with many attempts made to explain it. However, a complete understanding is yet to emerge. In this paper we...
Preprint
Decision tree learning is a widely used approach in machine learning, favoured in applications that require concise and interpretable models. Heuristic methods are traditionally used to quickly produce models with reasonably high accuracy. A commonly criticised point, however, is that the resulting trees may not necessarily be the best representati...
Conference Paper
Full-text available
Task difficulty (TD) reflects students' subjective judgement on the complexity of a task. We examine the task difficulty sequence data of 236 undergraduate students in a simulation-based Predict-Observe-Explain environment. The findings suggest that if students perceive the TDs as easy or hard, it may lead to poorer learning outcomes, while the med...
Preprint
Full-text available
Recent studies have shown that DNNs can be compromised by backdoor attacks crafted at training time. A backdoor attack installs a backdoor into the victim model by injecting a backdoor pattern into a small proportion of the training data. At test time, the victim model behaves normally on clean test data, yet consistently predicts a specific (likel...
Chapter
Virtual reality has gained popularity as an effective training platform in many fields including surgery. However, it has been shown that the availability of a simulator alone is not sufficient to promote practice. Therefore, simulator-based surgical curricula need to be developed and integrated into existing surgical training programs. As practice...
Preprint
Evaluating the robustness of a defense model is a challenging task in adversarial robustness research. Obfuscated gradients, a type of gradient masking, have previously been found to exist in many defense methods and cause a false signal of robustness. In this paper, we identify a more subtle situation called \emph{Imbalanced Gradients} that can al...
Preprint
Robust loss functions are essential for training accurate deep neural networks (DNNs) in the presence of noisy (incorrect) labels. It has been shown that the commonly used Cross Entropy (CE) loss is not robust to noisy labels. Whilst new loss functions have been designed, they are only partially robust. In this paper, we theoretically show by apply...
Article
Personalised analytics is a powerful technology that can be used to improve the career, lifestyle, and health of individuals by providing them with an in-depth analysis of their characteristics as compared to other people. Existing research has often focused on mining general patterns or clusters, but without the facility for customisation to an in...
Chapter
Full-text available
Task difficulty (TD) reflects students’ subjective judgement on the complexity of a task. We examine the task difficulty sequence data of 236 undergraduate students in a simulation-based Predict-Observe-Explain environment. The findings suggest that if students perceive the TDs as easy or hard, it may lead to poorer learning outcomes, while the med...
Article
Deep neural networks (DNNs) have become popular for medical image analysis tasks like cancer diagnosis and lesion detection. However, a recent study demonstrates that medical deep learning systems can be compromised by carefully-engineered adversarial examples/attacks with small imperceptible perturbations. This raises safety concerns about the dep...
Article
We study the predict+optimise problem, where machine learning and combinatorial optimisation must interact to achieve a common goal. These problems are important when optimisation needs to be performed on input parameters that are not fully observed but must instead be estimated using machine learning. We provide a novel learning technique for pred...
Conference Paper
Full-text available
Video is becoming a dominant medium for the delivery of educational material. Despite the widespread use of video for learning, there is still a lack of understanding about how best to help people learn in this medium. This study demonstrates the use of thermal camera as compared to traditional self-reported methods for assessing learners' cognitiv...
Preprint
Deep neural networks (DNNs) are known to be vulnerable to adversarial examples. Existing works have mostly focused on either digital adversarial examples created via small and imperceptible perturbations, or physical-world adversarial examples created with large and less realistic distortions that are easily identified by human observers. In this p...
Preprint
Deep neural networks (DNNs) are vulnerable to backdoor attacks which can hide backdoor triggers in DNNs by poisoning training data. A backdoored model behaves normally on clean test images, yet consistently predicts a particular target class for any test examples that contain the trigger pattern. As such, backdoor attacks are hard to detect, and ha...
Article
Full-text available
Users need to understand the predictions of a classifier, especially when decisions based on the predictions can have severe consequences. The explanation of a prediction reveals the reason why a classifier makes a certain prediction, and it helps users to accept or reject the prediction with greater confidence. This paper proposes an explanation m...
Article
The availability of large-scale spatio-temporal datasets along with the advancements in analytical models and tools have created a unique opportunity to create valuable insights into managing key areas of society from transportation and urban planning to epidemiology and natural disasters management. This has encouraged the practice of releasing/pu...
Preprint
Full-text available
Skip connections are an essential component of current state-of-the-art deep neural networks (DNNs) such as ResNet, WideResNet, DenseNet, and ResNeXt. Despite their huge success in building deeper and more powerful DNNs, we identify a surprising security weakness of skip connections in this paper. Use of skip connections allows easier generation of...
Article
One of the main challenges for online learners is knowing how to effectively manage their time. Highly autonomous settings, such as Massive Open Online Courses (MOOCs), put additional pressure on learners in this regard. However, little is known about how learners organize their time in terms of sessions or blocks of time across a MOOC. This study...
Conference Paper
Deep neural networks (DNNs) are known for their vulnerability to adversarial examples. These are examples that have undergone small, carefully crafted perturbations, and which can easily fool a DNN into making misclassifications at test time. Thus far, the field of adversarial research has mainly focused on image models, under either a white-box se...
Chapter
The local intrinsic dimensionality (LID) model enables assessment of the complexity of the local neighbourhood around a specific query object of interest. In this paper, we study variations in the LID of a query, with respect to different subspaces and local neighbourhoods. We illustrate the surprising phenomenon of how the LID of a query can subst...
Article
Full-text available
Despite the importance of attention in user performance, current methods for attention classification do not allow to discriminate between different attention types. We propose a novel method that combines thermal imaging and eye tracking to unobtrusively classify four types of attention: sustained, alternating, selective, and divided. We collected...
Preprint
Training accurate deep neural networks (DNNs) in the presence of noisy labels is an important and challenging task. Though a number of approaches have been proposed for learning with noisy labels, many open issues remain. In this paper, we show that DNN learning with Cross Entropy (CE) exhibits overfitting to noisy labels on some classes ("easy" cl...
Conference Paper
Full-text available
We consider the problem of learning a mapping directly from annotated music to waveforms, bypassing traditional single note synthesis. We propose a specific architecture based on WaveNet, a convolutional autoregressive generative model designed for text to speech. We investigate the representations learned by these models on music and concludethat...
Conference Paper
We study the predict+optimise problem, where machine learning and combinatorial optimisation must interact to achieve a common goal. These problems are important when optimisation needs to be performed on input parameters that are not fully observed but must instead be estimated using machine learning. Our contributions are two-fold: 1) we provide...
Conference Paper
Classifier explanations have been identified as a crucial component of knowledge discovery. Local explanations evaluate the behavior of a classifier in the vicinity of a given instance. A key step in this approach is to generate synthetic neighbors of the given instance. This neighbor generation process is challenging and it has considerable impact...
Preprint
Full-text available
Deep neural networks (DNNs) have become popular for medical image analysis tasks like cancer diagnosis and lesion detection. However, a recent study demonstrates that medical deep learning systems can be compromised by carefully-engineered adversarial examples/attacks, i.e., small imperceptible perturbations can fool DNNs to predict incorrectly. Th...
Conference Paper
Full-text available
This work aims to characterize students' writing processes using keystroke logs and understand how the extracted characteristics influence the text quality at specific moments of writing. Earlier works have proposed predictive models characterizing students' writing processes and mainly rely on distribution-based measures of pauses obtained from th...
Chapter
Virtual reality (VR) is increasingly being used as a training platform in many fields including surgery. However, practice on VR simulators alone is not sufficient to impart skills. Provision of performance feedback is essential to enable skill acquisition by ensuring that mistakes are identified and corrected, strengths are reinforced, and insight...
Preprint
Generative Adversarial Networks (GANs) are a powerful class of generative models. Despite their successes, the most appropriate choice of a GAN network architecture is still not well understood. GAN models for image synthesis have adopted a deep convolutional network architecture, which eliminates or minimizes the use of fully connected and pooling...
Preprint
Generative Adversarial Networks (GANs) are an elegant mechanism for data generation. However, a key challenge when using GANs is how to best measure their ability to generate realistic data. In this paper, we demonstrate that an intrinsic dimensional characterization of the data space learned by a GAN model leads to an effective evaluation metric f...
Article
Full-text available
The analysis of large-scale trajectory data has tremendous benefits for applications ranging from transportation planning to traffic management. A fundamental building block for the analysis of such data is the computation of similarity between trajectories. Existing work for similarity computation focuses mainly on the spatial aspects of trajector...
Conference Paper
Full-text available
With the increased reach and impact of video lectures, it is crucial to understand how they are experienced. Whereas previous studies typically present questionnaires at the end of the lecture, they fail to capture students' experience in enough granularity. In this paper we propose recording the lecture difficulty in real-time with a physical slid...
Preprint
Deep neural networks (DNNs) are known for their vulnerability to adversarial examples. These are examples that have undergone a small, carefully crafted perturbation, and which can easily fool a DNN into making misclassifications at test time. Thus far, the field of adversarial research has mainly focused on image models, under either a white-box s...
Chapter
Blockmodelling is an important technique for detecting underlying patterns in graphs. Existing blockmodelling algorithms are unsupervised and cannot take advantage of the existing information that might be available about objects that are known to be similar. This background information can help finding complex patterns, such as hierarchical or rin...