Deep Learning
Hypernetwork-based Meta-Learning for Low-Rank Physics-Informed Neural Networks
PINNs are, however, sharing the same weakness with coordinate-based MLPs (or INRs), which hinders the application of PINNs/INRs to more diverse applications; for a new data instance (e.g., a new PDE for PINNs or a new image for INRs), training a new neural network (typically from
A Active learning in more detail
Core-Set This method is based on the finding that the decision boundaries of convolutional neural networks are based on a small set of samples.
DataPerf: Benchmarks for Data-Centric AI Development Mark Mazumder
Machine learning research has long focused on models rather than datasets, and prominent datasets are used for common ML tasks without regard to the breadth, difficulty, and faithfulness of the underlying problems. Neglecting the fundamental importance of data has given rise to inaccuracy, bias, and fragility in real-world applications, and research is hindered by saturation across existing dataset benchmarks.
GlucoSynth: Generating Differentially-Private Synthetic Glucose Traces Josephine Lamp
GAN framework to generate synthetic glucose traces.
