Bridging Machine Learning and Sciences: Opportunities and Challenges
Not on the map. Why?
Abstract (arXiv)
The application of machine learning in sciences has seen exciting advances in recent years. As a widely applicable technique, anomaly detection has been long studied in the machine learning community. Especially, deep neural nets-based out-of-distribution detection has made great progress for high-dimensional data. Recently, these techniques have been showing their potential in scientific disciplines. We take a critical look at their applicative prospects including data universality, experimental protocols, model robustness, etc. We discuss examples that display transferable practices and domain-specific challenges simultaneously, providing a starting point for establishing a novel interdisciplinary research paradigm in the near future.
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 33 of its 58 references that are in the map. First posted on arXiv 24 Oct 2022.
Builds on
33 of 58 references.
References · 33
- 2017Attention Is All You Needcited by 59,932
- 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
- 2014Explaining and Harnessing Adversarial Examplescited by 7,287
- 2017A Unified Approach to Interpreting Model Predictionscited by 6,488
- 2017On Calibration of Modern Neural Networkscited by 4,860
- 2015Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learningcited by 4,416
- 2016Simple and Scalable Predictive Uncertainty Estimation using Deep Ensemblescited by 3,888
- 2015Domain-Adversarial Training of Neural Networkscited by 3,023
- 2016A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networkscited by 2,362
- 2019Invariant Risk Minimizationcited by 1,832
- 2019Explainable Artificial Intelligence (XAI): Concepts, Taxonomies, Opportunities and Challenges toward Responsible AIcited by 1,543
- 2019Can You Trust Your Model's Uncertainty? Evaluating Predictive Uncertainty Under Dataset Shiftcited by 1,274
21 more
- 2016Group Equivariant Convolutional Networkscited by 1,154
- 2021Geometric Deep Learning: Grids, Groups, Graphs, Geodesics, and Gaugescited by 1,131
- 2019Right for the Wrong Reasons: Diagnosing Syntactic Heuristics in Natural Language Inferencecited by 864
- 2021E(3)-Equivariant Graph Neural Networks for Data-Efficient and Accurate Interatomic Potentialscited by 701
- 2018Predictive Uncertainty Estimation via Prior Networkscited by 555
- 2019Likelihood Ratios for Out-of-Distribution Detectioncited by 451
- 2021Open-Set Recognition: a Good Closed-Set Classifier is All You Need?cited by 351
- 2019Cormorant: Covariant Molecular Neural Networkscited by 262
- 2018Domain Generalization via Conditional Invariant Representationcited by 146
- 2017Domain Adaptation by Using Causal Inference to Predict Invariant Conditional Distributionscited by 125
- 2020Lorentz Group Equivariant Neural Network for Particle Physicscited by 120
- 2015Approximating Likelihood Ratios with Calibrated Discriminative Classifierscited by 87
- 2021On the Impact of Spurious Correlation for Out-of-distribution Detectioncited by 68
- 2020Learning To Navigate The Synthetically Accessible Chemical Space Using Reinforcement Learningcited by 57
- 2016Learning to Pivot with Adversarial Networkscited by 55
- 2019Detecting semantic anomaliescited by 50
- 2020Viral Pneumonia Screening on Chest X-ray Images Using Confidence-Aware Anomaly Detectioncited by 28
- 2020Dealing with Nuisance Parameters using Machine Learning in High Energy Physics: a Reviewcited by 9
- 2022Invariant Representation Driven Neural Classifier for Anti-QCD Jet Taggingcited by 4
- 2019Interpretability Study on Deep Learning for Jet Physics at the Large Hadron Collidercited by 3
- 2021Towards Robustness of Neural Networkscited by 1
Built on by
Not cited yet.