78 citations · 297 across the 42 of their papers we have counts for
9 papers · 1 filter
Confidence Composition for Monitors of Verification Assumptions
Ivan Ruchkin, Matthew Cleaveland, Radoslav Ivanov +4
Closed-loop verification of cyber-physical systems with neural network controllers offers strong safety guarantees under certain assumptions. It is, however, difficult to determine…
Monotonic Safety for Scalable and Data-Efficient Probabilistic Safety Analysis
Matthew Cleaveland, Ivan Ruchkin, Oleg Sokolsky +1
Autonomous systems with machine learning-based perception can exhibit unpredictable behaviors that are difficult to quantify, let alone verify. Such behaviors are convenient to cap…
Detecting OODs as datapoints with High Uncertainty
Ramneet Kaur, Susmit Jha, Anirban Roy +3
Deep neural networks (DNNs) are known to produce incorrect predictions with very high confidence on out-of-distribution inputs (OODs). This limitation is one of the key challenges…
PAC Prediction Sets Under Covariate Shift
Sangdon Park, Edgar Dobriban, Insup Lee +1
An important challenge facing modern machine learning is how to rigorously quantify the uncertainty of model predictions. Conveying uncertainty is especially important when there a…
Improving Neural Network Robustness via Persistency of Excitation
Kaustubh Sridhar, Oleg Sokolsky, Insup Lee +1
Improving adversarial robustness of neural networks remains a major challenge. Fundamentally, training a neural network via gradient descent is a parameter estimation problem. In a…
ModelGuard: Runtime Validation of Lipschitz-continuous Models
Taylor J. Carpenter, Radoslav Ivanov, Insup Lee +1
This paper presents ModelGuard, a sampling-based approach to runtime model validation for Lipschitz-continuous models. Although techniques exist for the validation of many classes…
Are all outliers alike? On Understanding the Diversity of Outliers for Detecting OODs
Ramneet Kaur, Susmit Jha, Anirban Roy +2
Deep neural networks (DNNs) are known to produce incorrect predictions with very high confidence on out-of-distribution (OOD) inputs. This limitation is one of the key challenges i…
Confidence Calibration with Bounded Error Using Transformations
Sooyong Jang, Radoslav Ivanov, Insup Lee +1
As machine learning techniques become widely adopted in new domains, especially in safety-critical systems such as autonomous vehicles, it is crucial to provide accurate output unc…
Stacked LSTM Based Deep Recurrent Neural Network with Kalman Smoothing for Blood Glucose Prediction
Md Fazle Rabby, Yazhou Tu, Md Imran Hossen +3
Blood glucose (BG) management is crucial for type-1 diabetes patients resulting in the necessity of reliable artificial pancreas or insulin infusion systems. In recent years, deep…