Search Results for author:
Found 4 papers, 1 papers with code
Source Invariance and Probabilistic Transfer: A Testable Theory of Probabilistic Neural Representations
As animals interact with their environments, they must infer properties of their surroundings.
Implicit regularization of multi-task learning and finetuning in overparameterized neural networks
Our findings hold qualitatively for a deep architecture trained on image classification tasks, and our characterization of the nested feature selection regime motivates a modification to PT+FT that we find empirically improves performance.
The Implicit Bias of Gradient Descent on Generalized Gated Linear Networks
Understanding the asymptotic behavior of gradient-descent training of deep neural networks is essential for revealing inductive biases and improving network performance.
Evidence against implicitly recurrent computations in residual neural networks
To test this hypothesis, we manipulate the degree of weight sharing across layers in ResNets using soft gradient coupling.
