Search Results for author:
Found 8 papers, 5 papers with code
Manipulating Feature Visualizations with Gradient Slingshots
Deep Neural Networks (DNNs) are capable of learning complex and versatile representations, however, the semantic nature of the learned concepts remains unknown.
Labeling Neural Representations with Inverse Recognition
Deep Neural Networks (DNNs) demonstrate remarkable capabilities in learning complex hierarchical data representations, but the nature of these representations remains largely unknown.
Mark My Words: Dangers of Watermarked Images in ImageNet
The utilization of pre-trained networks, especially those trained on ImageNet, has become a common practice in Computer Vision.
DORA: Exploring Outlier Representations in Deep Neural Networks
Deep Neural Networks (DNNs) excel at learning complex abstractions within their internal representations.
Visualizing the Diversity of Representations Learned by Bayesian Neural Networks
Explainable Artificial Intelligence (XAI) aims to make learning machines less opaque, and offers researchers and practitioners various tools to reveal the decision-making strategies of neural networks.
Explaining Bayesian Neural Networks
Bayesian approaches such as Bayesian Neural Networks (BNNs) so far have a limited form of transparency (model transparency) already built-in through their prior weight distribution, but notably, they lack explanations of their predictions for given instances.
NoiseGrad: Enhancing Explanations by Introducing Stochasticity to Model Weights
For local explanation, stochasticity is known to help: a simple method, called SmoothGrad, has improved the visual quality of gradient-based attribution by adding noise to the input space and averaging the explanations of the noisy inputs.
How Much Can I Trust You? -- Quantifying Uncertainties in Explaining Neural Networks
Explainable AI (XAI) aims to provide interpretations for predictions made by learning machines, such as deep neural networks, in order to make the machines more transparent for the user and furthermore trustworthy also for applications in e. g. safety-critical areas.
