Related papers: Class Interference of Deep Neural Networks
Knowledge tracing---where a machine models the knowledge of a student as they interact with coursework---is a well established problem in computer supported education. Though effectively modeling student knowledge would have high…
A robust theoretical framework that can describe and predict the generalization ability of deep neural networks (DNNs) in general circumstances remains elusive. Classical attempts have produced complexity metrics that rely heavily on global…
Despite having excellent performances for a wide variety of tasks, modern neural networks are unable to provide a reliable confidence value allowing to detect misclassifications. This limitation is at the heart of what is known as an…
Deep neural networks perform exceptionally well on various learning tasks with state-of-the-art results. While these models are highly expressive and achieve impressively accurate solutions with excellent generalization abilities, they are…
This paper explores the bottleneck of feature representations of deep neural networks (DNNs), from the perspective of the complexity of interactions between input variables encoded in DNNs. To this end, we focus on the multi-order…
It is not fully understood why adversarial examples can deceive neural networks and transfer between different networks. To elucidate this, several studies have hypothesized that adversarial perturbations, while appearing as noises, contain…
Modern neural network architectures for large-scale learning tasks have substantially higher model complexities, which makes understanding, visualizing and training these architectures difficult. Recent contributions to deep learning…
Class imbalance is a common problem in the case of real-world object detection and classification tasks. Data of some classes is abundant making them an over-represented majority, and data of other classes is scarce, making them an…
We present an algorithm for computing class-specific universal adversarial perturbations for deep neural networks. Such perturbations can induce misclassification in a large fraction of images of a specific class. Unlike previous methods…
Regions of high-dimensional input spaces that are underrepresented in training datasets reduce machine-learnt classifier performance, and may lead to corner cases and unwanted bias for classifiers used in decision making systems. When these…
Daily operation of a large-scale experiment is a resource consuming task, particularly from perspectives of routine data quality monitoring. Typically, data comes from different sub-detectors and the global quality of data depends on the…
Neural networks for image classification tasks assume that any given image during inference belongs to one of the training classes. This closed-set assumption is challenged in real-world applications where models may encounter inputs of…
In the context of high usability in single-class anomaly detection models, recent academic research has become concerned about the more complex multi-class anomaly detection. Although several papers have designed unified models for this…
Catastrophic interference is common in many network-based learning systems, and many proposals exist for mitigating it. But, before we overcome interference we must understand it better. In this work, we provide a definition of interference…
Deep neural networks are highly expressive models that have recently achieved state of the art performance on speech and visual recognition tasks. While their expressiveness is the reason they succeed, it also causes them to learn…
Deep convolution networks have proved very successful with big datasets such as the 1000-classes ImageNet. Results show that the error rate increases slowly as the size of the dataset increases. Experiments presented here may explain why…
Supervised learning models often make systematic errors on rare subsets of the data. When these subsets correspond to explicit labels in the data (e.g., gender, race) such poor performance can be identified straightforwardly. This paper…
In last few years there are major changes and evolution has been done on classification of data. As the application area of technology is increases the size of data also increases. Classification of data becomes difficult because of…
The main requisite for fine-grained recognition task is to focus on subtle discriminative details that make the subordinate classes different from each other. We note that existing methods implicitly address this requirement and leave it to…
Several works have shown that the regularization mechanisms underlying deep neural networks' generalization performances are still poorly understood. In this paper, we hypothesize that deep neural networks are regularized through their…