A central factor in trustworthy autonomous systems is the presence of humans in different stages of an AI system’s deployment cycle – from data curation, to model training, evaluation, and deployment. In real world applications, an AI system requires different experts in each of these stages. For instance, in medical applications, doctors evaluate the decisions made by AI systems but are not well versed with its training. ML engineers can select the best possible models but may not be able to curate unbiased data for these models. Existing human-in-the-loop systems do not account for this variety in the required expertise. Since deep learning based AI systems require many specialized experts, their applicability is limited to only a few non-specialized applications. At OLIVES, we leverage limited experts to train large scalable systems that learn from limited data. We move away from a generic human-in-the-loop framework towards experts-in-the-loop.
1.Active Learning
a.Deployable Active Learning
i.Practical Active Learning for Seismic Interpretation
ii.Defining Information Content with Second Order Representation Shifts
iii.Forgetful Active Learning with Switch Events – Efficient Sampling for Out-of-Distribution Data
iv.Active Learning under distributional shift
b.Rethinking Active Learning Frameworks
i.Patient Aware Active Learning for OCT Classification
ii.Cost-Centered Active Learning in Video Sequences
iii.Continual Active Learning for OCT Scans
2.Interventionist Learning
a.Counterfactual Analysis on DHI data: A need for Causal Perspective for Risk Assessment
b.Explaining ML Models for Prospect Risk Analysis via Counterfactual Explanations
c.Gradients with confounding label encodings to probe effective expressivity of trained networks
d.Contrastive Explanations in Neural Networks
