Add to ORKGIn this paper, we investigate the principle that good explanations are hard to vary in the context of deep learning. We show that averaging gradients across examples -- akin to a logical OR of patterns -- can favor memorization and `patchwork' solutions that sew together different strategies, instead of identifying invariances. To inspect this, we first formalize a notion of consistency for minima of the loss surface, which measures to what extent a minimum appears only when examples are pooled. We then propose and experimentally validate a simple alternative algorithm based on a logical AND, that focuses on invariances and prevents memorization in a set of real-world tasks. Finally, using a synthetic dataset with a clear distinction betwee...
State-of-the-art deep learning methods achieve human-like performance on many tasks, but make errors...
The importance of explaining the outcome of a machine learning model, especially a black-box model, ...
International audienceRecent efforts have uncovered various methods for providing explanations that ...
The remarkable practical success of deep learning has revealed some major surprises from a theoretic...
The generalization mystery in deep learning is the following: Why do over-parameterized neural netwo...
Designing learning systems which are invariant to certain data transformations is critical in machin...
Unlabeled data exploitation and interpretability are usually both required in reality. They, however...
One of the primary challenges limiting the applicability of deep learning is its susceptibility to l...
With the rise of deep neural networks, the challenge of explaining the predictions of these networks...
Explaining black-box models such as deep neural networks is becoming increasingly important as it he...
This dissertation seeks to clarify and resolve a number of fundamental issues surrounding algorithmi...
With the rise of deep neural networks, the challenge of explaining the predictions of these networks...
In this thesis, Invariance in Deep Representations, we propose novel solutions to the problem of lea...
Successful reinforcement learning requires large amounts of data, compute, and some luck. We explore...
Deep neural networks have proven remarkably effective at solving many classification problems, but h...
State-of-the-art deep learning methods achieve human-like performance on many tasks, but make errors...
The importance of explaining the outcome of a machine learning model, especially a black-box model, ...
International audienceRecent efforts have uncovered various methods for providing explanations that ...
The remarkable practical success of deep learning has revealed some major surprises from a theoretic...
The generalization mystery in deep learning is the following: Why do over-parameterized neural netwo...
Designing learning systems which are invariant to certain data transformations is critical in machin...
Unlabeled data exploitation and interpretability are usually both required in reality. They, however...
One of the primary challenges limiting the applicability of deep learning is its susceptibility to l...
With the rise of deep neural networks, the challenge of explaining the predictions of these networks...
Explaining black-box models such as deep neural networks is becoming increasingly important as it he...
This dissertation seeks to clarify and resolve a number of fundamental issues surrounding algorithmi...
With the rise of deep neural networks, the challenge of explaining the predictions of these networks...
In this thesis, Invariance in Deep Representations, we propose novel solutions to the problem of lea...
Successful reinforcement learning requires large amounts of data, compute, and some luck. We explore...
Deep neural networks have proven remarkably effective at solving many classification problems, but h...
State-of-the-art deep learning methods achieve human-like performance on many tasks, but make errors...
The importance of explaining the outcome of a machine learning model, especially a black-box model, ...
International audienceRecent efforts have uncovered various methods for providing explanations that ...