Search Results for author:
Found 5 papers, 4 papers with code
Discovering State Variables Hidden in Experimental Data
All physical laws are described as relationships between state variables that give a complete and non-redundant description of the relevant system dynamics.
ClimateGAN: Raising Climate Change Awareness by Generating Images of Floods
Climate change is a major threat to humanity, and the actions required to prevent its catastrophic consequences include changes in both policy-making and individual behaviour.
Beyond Categorical Label Representations for Image Classification
Our experiments reveal that high dimensional, high entropy labels achieve comparable accuracy to text (categorical) labels on the standard image classification task, but features learned through our label representations exhibit more robustness under various adversarial attacks and better effectiveness with a limited amount of training data.
RealCause: Realistic Causal Inference Benchmarking
However, the best causal estimators on synthetic data are unlikely to be the best causal estimators on real data.
Evolution of Graph Classifiers
Our evolution mutates a population of neural networks to search the architecture and hyperparameter space.
Ranked #1 on
Graph Classification
on MUTAG
