Joshua Michalenko

Engineering · Physical Sciences

5h-index45citations23works0.32yr avg
OpenAlex↗ORCID↗Google Scholar↗

Accepting Students?

No reports yet. Know if this professor is taking students?

Research Topics

Fault Detection and Control Systems(5), Neural Networks and Applications(4), Machine Learning and Algorithms(4), Topic Modeling(3), Natural Language Processing Techniques(3)

Publications23 total

Conformal Anomaly Detection for Functional Data with Elastic Distance Metrics
arXiv (Cornell University)·2025Open Access
Quantifying Epistemic Uncertainty in Binary Classification via Accuracy Gain
Statistical Analysis and Data Mining The ASA Data Science Journal·2024· 1 citedOpen Access
Non-conformity Scores for High-Quality Uncertainty Quantification from Conformal Prediction
2024Open Access
Improving and Assessing the Quality of Uncertainty Quantification in Deep Learning
2023Open Access
Comparing the quality of neural network uncertainty estimates for classification problems
arXiv (Cornell University)·2023Open Access
Evaluation and Calibration of Epistemic Uncertainty
2023Open Access
Comparing the quality of neural network uncertainty estimates for classification problems
2022· 1 citedOpen Access
Comparing the Quality of Neural Network Uncertainty Estimates for Classification Problems.
2022Open Access
GraphAlign: Graph-Enabled Machine Learning for Seismic Event Filtering
2022Open Access
Data Fusion via Neural Network Entropy Minimization for Target Detection and Multi-Sensor Event Classification
2022· 2 citedOpen Access
Assessing the Quality of Uncertainty Estimates in Deep Learning.
2022Open Access
Semi-supervised Bayesian Low-shot Learning
2021Open Access
Machine Learning Predictions of Transition Probabilities in Atomic Spectra
Atoms·2021· 5 citedOpen Access
Semisupervised Learning for Seismic Monitoring Applications
Seismological Research Letters·2020· 8 citedOpen Access
Multimodal Data Fusion via Entropy Minimization
2020· 1 cited
Multimodal Data Fusion via Entropy Minimization
2020Open Access
Representing Formal Languages: A Comparison Between Finite Automata and Recurrent Neural Networks
arXiv (Cornell University)·2019· 10 citedOpen Access
Representing Formal Languages: A Comparison Between Finite Automata and\n Recurrent Neural Networks
arXiv (Cornell University)·2019· 7 citedOpen Access
Finite Automata Can be Linearly Decoded from Language-Recognizing RNNs
International Conference on Learning Representations·2019
Data-Mining Textual Responses to Uncover Misconception Patterns
2017· 9 cited
page 1 of 2Next →

Frequent Co-authors

Tyler Ganter(7), Jason Adams(6), Daniel Ries(6), Richard G. Baraniuk(5), Andrew Lan(4), Lisa Linville(4), Dylan Anderson(4), Jason Y. Adams(4), Christopher Qian(3), Feng Liang(3), Brandon Berman(3), Rashad Baiyasi(3), Ameesh Shah(2), Abhinav Verma(2), Swarat Chaudhuri(2), Rashad Imad-Fayez Baiyasi(2), Ankit Patel(1), Jennifer Galasso(1), Timothy J. Draelos(1), Ameesh Shah(1)