Robustness (evolution)
View article
mixup: Beyond Empirical Risk Minimization Open
Large deep neural networks are powerful, but exhibit undesirable behaviors such as memorization and sensitivity to adversarial examples. In this work, we propose mixup, a simple learning principle to alleviate these issues. In essence, mix…
View article
Unobservable Selection and Coefficient Stability: Theory and Evidence Open
A common approach to evaluating robustness to omitted variable bias is to observe coefficient movements after inclusion of controls. This is informative only if selection on observables is informative about selection on unobservables. Alth…
View article
On Assessing ML Model Robustness: A Methodological Framework (Academic Track) Open
Due to their uncertainty and vulnerability to adversarial attacks, machine learning (ML) models can lead to severe consequences, including the loss of human life, when embedded in safety-critical systems such as autonomous vehicles. Theref…
View article
Software update: The <span>ORCA</span> program system—Version 5.0 Open
Version 5.0 of the ORCA quantum chemistry program suite was released in July 2021. ORCA 5.0 represents a major improvement over all previous versions of ORCA and features (1) highly improved performance, (2) increased numerical robustness,…
View article
SegFormer: Simple and Efficient Design for Semantic Segmentation with\n Transformers Open
We present SegFormer, a simple, efficient yet powerful semantic segmentation\nframework which unifies Transformers with lightweight multilayer perception\n(MLP) decoders. SegFormer has two appealing features: 1) SegFormer comprises a\nnove…
View article
Simple and Scalable Predictive Uncertainty Estimation using Deep\n Ensembles Open
Deep neural networks (NNs) are powerful black box predictors that have\nrecently achieved impressive performance on a wide spectrum of tasks.\nQuantifying predictive uncertainty in NNs is a challenging and yet unsolved\nproblem. Bayesian N…
View article
Classification assessment methods Open
Classification techniques have been applied to many applications in various fields of sciences. There are several ways of evaluating classification algorithms. The analysis of such metrics and its significance must be interpreted correctly…
View article
Sensitivity Analyses for Robust Causal Inference from Mendelian Randomization Analyses with Multiple Genetic Variants Open
Mendelian randomization investigations are becoming more powerful and simpler to perform, due to the increasing size and coverage of genome-wide association studies and the increasing availability of summarized data on genetic associations…
View article
SMOTE for Learning from Imbalanced Data: Progress and Challenges, Marking the 15-year Anniversary Open
The Synthetic Minority Oversampling Technique (SMOTE) preprocessing algorithm is considered "de facto" standard in the framework of learning from imbalanced data. This is due to its simplicity in the design of the procedure, as well as its…
View article
A brief introduction to mixed effects modelling and multi-model inference in ecology Open
The use of linear mixed effects models (LMMs) is increasingly common in the analysis of biological data. Whilst LMMs offer a flexible approach to modelling a broad range of data types, ecological data are often complex and require complex …
View article
Soft Robotic Grippers Open
Advances in soft robotics, materials science, and stretchable electronics have enabled rapid progress in soft grippers. Here, a critical overview of soft robotic grippers is presented, covering different material sets, physical principles,…
View article
A Survey of Autonomous Driving: <i>Common Practices and Emerging Technologies</i> Open
Automated driving systems (ADSs) promise a safe, comfortable and efficient\ndriving experience. However, fatalities involving vehicles equipped with ADSs\nare on the rise. The full potential of ADSs cannot be realized unless the\nrobustnes…
View article
Towards Deep Learning Models Resistant to Adversarial Attacks Open
Recent work has demonstrated that deep neural networks are vulnerable to adversarial examples---inputs that are almost indistinguishable from natural data and yet classified incorrectly by the network. In fact, some of the latest findings …
View article
IUPred2A: context-dependent prediction of protein disorder as a function of redox state and protein binding Open
The structural states of proteins include ordered globular domains as well as intrinsically disordered protein regions that exist as highly flexible conformational ensembles in isolation. Various computational tools have been developed to …
View article
Designing Difference in Difference Studies: Best Practices for Public Health Policy Research Open
The difference in difference (DID) design is a quasi-experimental research design that researchers often use to study causal relationships in public health settings where randomized controlled trials (RCTs) are infeasible or unethical. How…
View article
Non-normal data: Is ANOVA still a valid option? Open
The results showed that in terms of Type I error the F-test was robust in 100% of the cases studied, independently of the manipulated conditions.
View article
Topological insulator laser: Experiments Open
Topological protection for lasers Ideas based on topology, initially developed in mathematics to describe the properties of geometric space under deformations, are now finding application in materials, electronics, and optics. The main dri…
View article
Robustness of linear mixed‐effects models to violations of distributional assumptions Open
Linear mixed‐effects models are powerful tools for analysing complex datasets with repeated or clustered observations, a common data structure in ecology and evolution. Mixed‐effects models involve complex fitting procedures and make sever…
View article
High Resolution Model Intercomparison Project (HighResMIP v1.0) for CMIP6 Open
Robust projections and predictions of climate variability and change, particularly at regional scales, rely on the driving processes being represented with fidelity in model simulations. The role of enhanced horizontal resolution in improv…
View article
DIANA-TarBase v8: a decade-long collection of experimentally supported miRNA–gene interactions Open
This FAIRsharing record describes: DIANA-TarBase is a reference database that indexes experimentally-supported microRNA (miRNA) targets. It integrates information on cell-type specific miRNA–gene regulation and includes miRNA-binding locat…
View article
Robust Speech Recognition via Large-Scale Weak Supervision Open
We study the capabilities of speech processing systems trained simply to predict large amounts of transcripts of audio on the internet. When scaled to 680,000 hours of multilingual and multitask supervision, the resulting models generalize…
View article
Ensemble Adversarial Training: Attacks and Defenses Open
Adversarial examples are perturbed inputs designed to fool machine learning models. Adversarial training injects such examples into training data to increase robustness. To scale this technique to large datasets, perturbations are crafted …
View article
Network analysis of multivariate data in psychological science Open
In recent years, network analysis has been applied to identify and analyse patterns of statistical association in multivariate psychological data. In these approaches, network nodes represent variables in a data set, and edges represent pa…
View article
Penalising Model Component Complexity: A Principled, Practical Approach to Constructing Priors Open
In this paper, we introduce a new concept for constructing prior distributions. We exploit the natural nested structure inherent to many model components, which defines the model component to be a flexible extension of a base model. Proper…
View article
<i>Planck</i>2018 results Open
We describe the legacy Planck cosmic microwave background (CMB) likelihoods derived from the 2018 data release. The overall approach is similar in spirit to the one retained for the 2013 and 2015 data release, with a hybrid method using di…
View article
LAION-5B: An open large-scale dataset for training next generation image-text models Open
Groundbreaking language-vision architectures like CLIP and DALL-E proved the utility of training on large amounts of noisy image-text data, without relying on expensive accurate labels used in standard vision unimodal supervised learning. …
View article
Linear discriminant analysis: A detailed tutorial Open
Linear Discriminant Analysis (LDA) is a very common \ntechnique for dimensionality reduction problems as a preprocessing \nstep for machine learning and pattern classification \napplications. At the same time, it is usually used as a \nbla…
View article
Particle Image Velocimetry for MATLAB: Accuracy and enhanced algorithms in PIVlab Open
PIVlab is a free toolbox and app for MATLAB®. It is used to perform Particle Image Velocimetry (PIV) with image data: A light sheet illuminates particles that are suspended in a fluid. A digital camera records a series of images of the ill…
View article
Mixup: Beyond empirical risk minimization Open
Large deep neural networks are powerful, but exhibit undesirable behaviors such as memorization and sensitivity to adversarial examples. In this work, we propose mixup, a simple learning principle to alleviate these issues. In essence, mix…
View article
Theoretically Principled Trade-off between Robustness and Accuracy Open
We identify a trade-off between robustness and accuracy that serves as a guiding principle in the design of defenses against adversarial examples. Although this problem has been widely studied empirically, much remains unknown concerning t…