User profiles for "author:Sonali Parbhoo"
Sonali ParbhooAssistant Professor, Imperial College London Verified email at imperial.ac.uk Cited by 935 |
Beyond sparsity: Tree regularization of deep models for interpretability
The lack of interpretability remains a key barrier to the adoption of deep models in many
applications. In this work, we explicitly regularize deep models so human users might step …
applications. In this work, we explicitly regularize deep models so human users might step …
Addressing leakage in concept bottleneck models
Abstract Concept bottleneck models (CBMs) enhance the interpretability of their predictions
by first predicting high-level concepts given features, and subsequently predicting outcomes …
by first predicting high-level concepts given features, and subsequently predicting outcomes …
[HTML][HTML] Determinants of HIV-1 reservoir size and long-term dynamics during suppressive ART
N Bachmann, C Von Siebenthal, V Vongrad… - Nature …, 2019 - nature.com
The HIV-1 reservoir is the major hurdle to a cure. We here evaluate viral and host
characteristics associated with reservoir size and long-term dynamics in 1,057 individuals …
characteristics associated with reservoir size and long-term dynamics in 1,057 individuals …
[HTML][HTML] Real-time prediction of COVID-19 related mortality using electronic health records
Abstract Coronavirus disease 2019 (COVID-19) is a respiratory disease with rapid human-to-
human transmission caused by the severe acute respiratory syndrome coronavirus 2 (SARS …
human transmission caused by the severe acute respiratory syndrome coronavirus 2 (SARS …
[HTML][HTML] Combining kernel and model based learning for HIV therapy selection
We present a mixture-of-experts approach for HIV therapy selection. The heterogeneity in
patient data makes it difficult for one particular model to succeed at providing suitable …
patient data makes it difficult for one particular model to succeed at providing suitable …
Interpretable off-policy evaluation in reinforcement learning by highlighting influential transitions
Off-policy evaluation in reinforcement learning offers the chance of using observational data
to improve future outcomes in domains such as healthcare and education, but safe …
to improve future outcomes in domains such as healthcare and education, but safe …
The unintended consequences of discount regularization: Improving regularization in certainty equivalence reinforcement learning
Discount regularization, using a shorter planning horizon when calculating the optimal
policy, is a popular choice to restrict planning to a less complex set of policies when …
policy, is a popular choice to restrict planning to a less complex set of policies when …
Regional tree regularization for interpretability in deep neural networks
The lack of interpretability remains a barrier to adopting deep neural networks across many
safety-critical domains. Tree regularization was recently proposed to encourage a deep …
safety-critical domains. Tree regularization was recently proposed to encourage a deep …
Optimizing for interpretability in deep neural networks with tree regularization
Deep models have advanced prediction in many domains, but their lack of interpretability
remains a key barrier to the adoption in many real world applications. There exists a large …
remains a key barrier to the adoption in many real world applications. There exists a large …
[HTML][HTML] Preferential mixture-of-experts: Interpretable models that rely on human expertise as much as possible
Abstract We propose Preferential MoE, a novel human-ML mixture-of-experts model that
augments human expertise in decision making with a data-based classifier only when …
augments human expertise in decision making with a data-based classifier only when …