1 code implementation • 8 Mar 2021 • Cecilia Summers, Michael J. Dinneen
In this work, we establish an experimental protocol for understanding the effect of optimization nondeterminism on model diversity, allowing us to isolate the effects of a variety of sources of nondeterminism.
no code implementations • 1 Jan 2021 • Cecilia Summers, Michael J. Dinneen
In this work, we establish an experimental protocol for understanding the effect of optimization nondeterminism on model diversity, which allows us to study the independent effects of a variety of sources of nondeterminism.
no code implementations • 10 Jun 2019 • Cecilia Summers, Michael J. Dinneen
While great progress has been made at making neural networks effective across a wide range of visual tasks, most models are surprisingly vulnerable.
2 code implementations • ICLR 2020 • Cecilia Summers, Michael J. Dinneen
A key component of most neural network architectures is the use of normalization layers, such as Batch Normalization.
1 code implementation • 29 May 2018 • Cecilia Summers, Michael J. Dinneen
In order to reduce overfitting, neural networks are typically trained with data augmentation, the practice of artificially generating additional training data via label-preserving transformations of existing training examples.