Crowdsourcing can improve scientific investigation by enabling reproducibility and transparency.
problem Current research methods lack reproducibility and transparency, leading to unreliable decisions.
method Next-generation investigative approach leveraging human diversity, micro-specialized crowds, and computer-assisted control methods.
result The Theory of Enablers provides specific cognitive and non-cognitive enablers for crowd-based scientific investigation.
Galactica learns from scientific literature to help researchers.
problem Information overload in scientific literature makes it hard to find useful insights.
method Trained on a large corpus of scientific papers, reference material, and knowledge bases.
result Outperforms existing models on various scientific tasks, including LaTeX equations and mathematical reasoning.
Study examines scientific research on Bitcoin across various disciplines.
problem Limited time but large number of papers on Bitcoin.
method Bibliometric analysis of papers indexed in Web of Science Core Collection.
result Observes research clusters, emerging topics, and leading scholars.
TGDS integrates scientific theory into data science for better model interpretation and discovery.
problem Limited applicability of data science models in scientific problems involving complex phenomena.
method Integrating scientific theory into data science models to improve model effectiveness and interpretability.
result TGDS aims to advance scientific understanding by discovering novel insights.
Before retiring, looking back to forty years of writing and publishing scientific papers, I decided to present to the scientific community a selection of my scientific works. I chose mostly articles published in prestigious journals or Proceedings that made a certain impact in the scientific world. I have selected thir…
Paper proposes a method to estimate scientific parameters in hybrid models without relying on model architecture.
problem Estimating unknown parameters in hybrid models combining machine learning and scientific models.
method Sharpness-aware minimization adapted for hybrid modeling, focusing on model simplicity.
result Demonstrates effectiveness of SAM-based hybrid model learning for scientific parameter estimation.
Researchers often summarize their work in the form of posters. Posters provide a coherent and efficient way to convey core ideas from scientific papers. Generating a good scientific poster, however, is a complex and time consuming cognitive task, since such posters need to be readable, informative, and visually aesthet…
Extract keyphrases and relations from scientific documents.
problem Understanding which publications describe which processes, tasks, and materials.
method Evaluated 26 submissions across 3 scenarios.
result Task and findings relevant for researchers and information extraction communities.
Visuals in scientific papers are used to express complex ideas; this study uses them to identify knowledge domains.
problem Scientific figures are underutilized in literature analysis.
method Encoded scientific figures into visual signatures and used distances between signatures to compare communities of practice.
result Figures can differentiate knowledge domains as effectively as text or citation patterns.
Social media enhances or diminishes scientific status, depending on usage.
problem Impact of social media on scientific stratification and mobility.
method Logistic Attribution Analysis combining statistical and machine learning methods.
result Social media promotes stratification and mobility, but beyond a threshold, it negatively impacts status.
Paper presents a workflow for reliable unsupervised learning in science.
problem Lack of standardization in unsupervised learning workflows for reproducible scientific discoveries.
method Structured workflow including data preparation, modeling, validation, and communication.
result Illustrates the importance of validation in unsupervised learning.
TopicEq model generates equations and text from scientific papers.
problem Communicating ideas in scientific texts using both mathematics and text.
method Joint topic and equation generation model using correlated topic model and RNN.
result Joint model outperforms existing topic and equation models for scientific texts.
The study reveals nations drive scientific research for social and economic interests.
problem Why do nations produce scientific research?
method Synthesizes previous concepts of science and scientific research, defines them, and identifies key drivers.
result Scientific research is driven by nations' social and economic interests, not just for philosophical inquiries.
Develops a new dataset and model for summarizing scientific papers.
problem Lack of large datasets for summarizing scientific papers.
method Exploits author-provided summaries, uses neural sentence encoding and summarisation features.
result Models that encode sentences and their context perform best, significantly outperforming baselines.
The paper argues for prioritizing identifying structure over complex models for scientific discovery.
problem Underdetermination of mechanisms in high-dimensional data, leading to unreliable explanations.
method Proposes concrete standards for 'mechanistic ML' to avoid collapsing explanations.
result Large language models (LLMs) can collapse large equivalence classes of explanations, making it hard to distinguish between mechanisms.
This paper advocates for applying scientific method principles to machine learning.
problem Aligning machine learning with scientific rigor, safety, and interpretability.
method Identifying and applying scientific method stages (hypothesis formulation, testing, uncertainty estimation) to machine learning.
result Machine learning researchers should adopt practices from other scientific domains to enhance understanding and reliability.
Paper develops an attention mechanism for long-term scientific impact prediction.
problem Predicting the long-term impact of scientific papers based on citation records.
method Develops an attention mechanism to predict long-term scientific impact.
result Emphasizing the limited attention can better stand on the shoulders of giants.
Physics-guided models improve lake temperature and quality predictions.
problem Predicting and monitoring water temperature and quality in lakes.
method Combining physics-based models and recurrent neural networks with physical constraints.
result Improved prediction accuracy and scientific consistency.
This work uses scientific constraints to validate neural network predictions in fusion physics.
problem Verifying the scientific plausibility of neural network predictions in fusion physics.
method Using known scientific constraints as a validation tool.
result Validated neural network predictions in fusion physics using scientific constraints.
In this paper we analyze both the scientific activities of Cahit Arf, a Turkish mathematician, and the social context in which he worked. We also discuss his work and social environment leading to the discovery of Arf invariant, Arf rings, Arf closure and Hasse-Arf theorem.
Paper outlines a new mathematical language for experiments.
problem Formalizing the scientific process for automation.
method Formulates the scientific process in precise mathematical language.
result Novel contributions in data processing, bias variance, and deficiency.
xVal tokenizes numbers continuously for better scientific model training.
problem Lack of continuous numerical tokenization for scientific datasets in LLMs.
method xVal: Continuous numerical tokenization strategy.
result xVal outperforms other numerical tokenization methods on scientific datasets.
PGNN combines physics models with neural nets for lake temperature prediction.
problem Lake temperature modeling with physical constraints.
method Physics-guided neural networks using hybrid modeling and physics-based loss functions.
result PGNN improves generalizability and scientific consistency in lake temperature predictions.
PNNs model aleatoric uncertainty in scientific machine learning with high accuracy.
problem Aleatoric uncertainty in scientific systems with unequal variance.
method Developed a probabilistic distance metric to optimize PNN architecture and used it in material science applications.
result PNNs yield remarkably accurate output mean estimates and high correlation in predicted intervals.
Machine learning aids scientific discoveries by explaining complex data.
problem Extracting scientific insights from complex data.
method Combining machine learning with domain knowledge for transparency, interpretability, and explainability.
result Enhanced scientific consistency through machine learning and domain knowledge integration.
FRACTI framework supports large-scale collaboration and transparent investigation in finance.
problem Complex, multidisciplinary research in finance requires robust support systems.
method Defines scientific support systems, shares contributions, classifies facets, and outlines a meta-model.
result FRACTI enables provenance tracking and large-scale investigation in computational finance.
This paper provides a guide to feature importance methods for better scientific inference.
problem Limited understanding of data-generating process due to opaque ML model mechanisms.
method Comprehensive review and new proofs of global feature importance methods.
result Facilitates a thorough understanding and concrete recommendations for FI methods.
AutoSciDACT detects scientific anomalies in noisy data.
problem Detecting anomalies in large, noisy scientific datasets.
method Contrastive pre-training for low-dimensional data representations, two-sample test using NPLM.
result Strong sensitivity to small anomalies across various scientific domains.
MDNs offer a data-efficient alternative to diffusion and flow models for multimodal scientific learning.
problem Capturing multimodal conditional uncertainty in scientific inverse problems.
method Mixture Density Networks (MDNs) as explicit parametric density estimators.
result MDNs achieve superior generalization, interpretability, and sample efficiency in scientific tasks.
Survey of deep learning models for scientific discovery.
problem Identifying which scientific problems are most suitable for deep learning.
method Overview of deep learning models, tasks, training methods, and techniques.
result Helps accelerate deep learning use in scientific domains.
New framework compresses and recovers scientific data efficiently.
problem Efficiently managing and recovering from large scientific datasets.
method Grounded in learning exponential families, preserves uncertainty and supports trade-offs.
result Preserves physical features and quantities of interest in compressed representations.
Hurd's career overview and publications listed.
problem None explicitly stated in the abstract.
method Not applicable as it's an introduction.
result No specific key result mentioned.
This thesis advances algorithms and software for QMC, GP, and sciML.
problem Efficient high-dimensional integration, interpolation, and PDE modeling.
method Developed new algorithms and software for QMC, GP, and sciML.
result Efficient and accurate methods for high-dimensional problems.
New AI approach improves quantum device calibration by leveraging prior scientific discoveries.
problem Lack of abundant data in scientific disciplines hinders model generalizability.
method Introduces a new machine learning approach that combines prior scientific knowledge with data.
result Accuracy in predicting quantum device energy spectrum surpasses current state-of-the-art by over 20%.
New method for PINNs uncertainty quantification without prior distribution.
problem Lack of reliable uncertainty quantification for PINNs.
method Extended fiducial inference with narrow-neck hyper-network.
result Construction of honest confidence sets based on observed data.
A dataset for evaluating engagement with scientific video lectures.
problem Challenges in managing learning resources due to rapid creation of video lectures.
method Introduction of VLEngagement dataset with content-based and video-specific features, and metrics related to user engagement.
result The largest and most diverse publicly available dataset for understanding context-agnostic engagement in video lectures.
This study compares Matlab and OpenCV for machine learning algorithms.
problem Comparing execution speeds of Matlab and OpenCV for machine learning.
method 20 real datasets, 20 different machine learning algorithms.
result OpenCV is significantly faster than Matlab in execution.
Develops a Bayesian framework for symbolic regression of scientific expressions.
problem Lack of principled uncertainty quantification and interpretability in existing symbolic regression methods.
method Hierarchical Bayesian framework with tree-structured symbolic expressions and Markov chain Monte Carlo inference.
result Robust performance on various datasets, including single-atom catalysis.
EduQG generates better educational questions by pre-training on scientific text.
problem Improving the quality of educational questions for scalable self-assessment.
method Adapting a large language model for educational question generation, pre-trained on scientific text.
result EduQG produces superior educational questions compared to baseline models.
SOS-VAE improves generative models for scientific applications by correcting decoder bias.
problem Bias in generative parameters due to supervised learning in VAEs.
method Develops SOS-VAE framework to influence decoder for predictive latent representation.
result Ensures reliable generative parameters for scientific applications.
Convolutional neural networks win SemEval-2017 for scientific relation extraction.
problem Extracting relations between scientific concepts from scholarly articles.
method Convolutional neural network model for relation extraction.
result Ranked first in SemEval-2017 Task 10 for relation extraction in scientific articles.
Paper optimizes training data distribution for better model performance across various deployment conditions.
problem Improving model accuracy when deployed with parameters far from training data.
method Developed adaptive algorithms based on bilevel or alternating optimization in the space of probability measures.
result Optimized training distributions lead to models with improved sample complexity and robustness to distribution shift.
Differentiable programming aids in solving differential equations and their sensitivities.
problem Computing gradients of numerical solutions of differential equations.
method Review of existing techniques and mathematical foundations.
result Established a coherent framework for combining differential equations with data-driven approaches.
Economics does not need a scientific revolution. Economics needs accurate measurements according to high standards of natural sciences and meticulous work on revealing empirical relationships between measured variables.
Deep neural nets improve KBC for scientific articles.
problem Lack of labelled data for keyphrase boundary classification.
method Multi-task learning with deep recurrent neural networks.
result Multi-task models significantly outperform previous methods.
PIMA autoencoders discover shared features in multimodal scientific data.
problem Discovering shared information in high-throughput scientific datasets.
method Physics-informed multimodal autoencoders (PIMA) with Gaussian mixture prior and product of experts formulation.
result Accurate cross-modal inference between images and mechanical stress-strain response in lattice metamaterials.
SentiCite analyzes citations for sentiment and nature, improving on existing methods.
problem Identifying quality scientific work amidst many citations.
method Sentiment analysis of citations with motivation detection.
result SentiCite outperforms state-of-the-art methods with a F1-measure of 0.71.
Machine learning needs stronger mathematical foundations for scientific applications.
problem Lack of rigorous mathematical foundations for machine learning in scientific and engineering contexts.
method Further mathematical developments and incorporation of prior knowledge and inductive biases.
result Stronger mathematical rigor is essential for reliable and interpretable machine learning results in scientific fields.