Thomas J. Pfaff
Ithaca College
10 Papers
18 Citations
Thomas J. Pfaff is an academic researcher from Ithaca College. The author has contributed to research in topics: Computer science & Surrogate model. The author has an hindex of 4, co-authored 10 publications. Previous affiliations of Thomas J. Pfaff include Bielefeld University.
Chat about Author
Papers
•Posted Content
Information Maximization Clustering via Multi-View Self-Labelling.
TL;DR: Li et al. as discussed by the authors proposed a single-phase clustering method that simultaneously learns meaningful representations and assigns the corresponding annotations by integrating a discrete representation into the self-supervised paradigm through a classifier net.
19
A latent batch-constrained deep reinforcement learning approach for precision dosing clinical decision support
TL;DR: Wang et al. as mentioned in this paper proposed an individualized dosing policy to determine the optimal initial dose and minimize the risk of mis-dosing, as well as preventing the patients from late complications associated with medications dosing.
18
Hybrid attention-based transformer block model for distant supervision relation extraction
TL;DR: Zhang et al. as mentioned in this paper proposed a new framework using hybrid attention-based Transformer block with multi-instance learning for distant supervision relation extraction, which mainly utilizes multi-head self-attention to capture syntactic information at the word level.
A latent batch-constrained deep reinforcement learning approach for precision dosing clinical decision support
TL;DR: Wang et al. as discussed by the authors proposed an individualized dosing policy to determine the optimal initial dose and minimize the risk of mis-dosing, as well as preventing the patients from late complications associated with medications dosing.
4
•Posted Content
A Data Stream Ensemble Assisted Multifactorial Evolutionary Algorithm for Offline Data-driven Dynamic Optimization
TL;DR: A data-driven optimization algorithm to deal with the challenges presented by the dynamic environments by adopting a data stream ensemble learning method to train the surrogates and a multi-task evolutionary algorithm is employed to simultaneously optimize the problems in the past environments assisted by the ensemble surrogate.
3