Search Results for author:
Found 4 papers, 0 papers with code
On Plasticity, Invariance, and Mutually Frozen Weights in Sequential Task Learning
In particular, we show that, when using weight decay, weights in successive layers of a deep network may become "mutually frozen".
Quantifying the effect of representations on task complexity
To quantify this alignment effect of data representations on the difficulty of a learning task, we make use of an existing task complexity score and show its connection to the representation-dependent information coding length of the input.
The Frechet Distance of training and test distribution predicts the generalization gap
Empirically across several data domains, we substantiate this viewpoint by showing that test performance correlates strongly with the distance in data distributions between training and test set.
Inspiring Computer Vision System Solutions
Reviewing this project with modern eyes provides us with the opportunity to reflect on several issues, relevant now as then to the field of computer vision and research in general, that go beyond the technical aspects of the work.
