Deep Learning
RED: Looking for Redundancies for Data-Free Structured Compression of Deep Neural Networks
Deep Neural Networks (DNNs) are ubiquitous in today's computer vision landscape, despite involving considerable computational costs. The mainstream approaches for runtime acceleration consist in pruning connections ( unstructured pruning) or, better, filters ( structured pruning), both often requiring data to retrain the model.
Finding Naturally Occurring Physical Backdoors in Image Datasets Emily Wenger University of Chicago Roma Bhattacharjee
Extensive literature on backdoor poison attacks has studied attacks and defenses for backdoors using "digital trigger patterns." In contrast, "physical backdoors" use physical objects as triggers, have only recently been identified, and are qualitatively different enough to resist most defenses targeting digital trigger backdoors. Research on physical backdoors is limited by access to large datasets containing real images of physical objects co-located with misclassification targets . Building these datasets is time-and labor-intensive. This work seeks to address the challenge of accessibility for research on physical backdoor attacks.
A Practical Debugging Tool for the Training of Deep Neural Networks Supplementary Material Checklist
Do the main claims made in the abstract and introduction accurately reflect the paper's Did you describe the limitations of your work? Did you discuss any potential negative societal impacts of your work? In general, we believe, this work will have an overall positive impact as it can help shed light into the black-box that is deep learning. If you ran experiments... (a) Did you include the code, data, and instructions needed to reproduce the main experimental results (either in the supplemental material or as a URL)? [Y es] All experimental results, as well as the complete code base to reproduce them can be Did you specify all the training details (e.g., data splits, hyperparameters, how they were chosen)? Did you report error bars (e.g., with respect to the random seed after running experiments multiple times)?
A Practical Debugging Tool for the Training of Deep Neural Networks Frank Schneider University of Tübingen Maria-von-Linden-Straße 6 Tübingen, Germany
When engineers train deep learning models, they are very much "flying blind".
Experimental design for MRI by greedy policy search
In today's clinical practice, magnetic resonance imaging (MRI) is routinely accelerated through subsampling of the associated Fourier domain.
Almost Surely Stable Deep Dynamics
We introduce a method for learning provably stable deep neural network based dynamic models from observed data.