Search Results for author:
Found 3 papers, 0 papers with code
A Meta-Learned Neuron model for Continual Learning
Continual learning is the ability to acquire new knowledge without forgetting the previously learned one, assuming no further access to past training data.
On the inductive biases of deep domain adaptation
Domain alignment is currently the most prevalent solution to unsupervised domain-adaptation tasks and are often being presented as minimizers of some theoretical upper-bounds on risk in the target domain.
On the Theoretical Equivalence of Several Trade-Off Curves Assessing Statistical Proximity
The recent advent of powerful generative models has triggered the renewed development of quantitative measures to assess the proximity of two probability distributions.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
