Noise Sensitivity and Stability of Deep Neural Networks for Binary Classification
A first step is taken towards understanding often observed non-robustness phenomena of deep neural net (DNN) classifiers. This is done from the perspective of Boolean functions by asking if certain sequences of Boolean functions represented by common DNN models are noise sensitive or noise stable, concepts defined in the Boolean function literature. Due to the natural randomness in DNN models, these concepts are extended to annealed and quenched versions. Here we sort out the relation between these definitions and investigate the properties of two standard DNN architectures, the fully connected and convolutional models, when initiated with Gaussian weights.
Code (0)
등록된 구현이 없습니다.
Tasks
Binary ClassificationSensitivitySimilar Papers 제목 키워드 기반
Color Texture Classification Based on Proposed Impulse-Noise Resistant Color Local Binary Patterns and Significant Points Selection Algorithm
The main aim of this paper is to propose a color texture classification approach which uses color sensor information and texture features jointly. High accuracy, low noise sensitivity and low computational complexity are…
General ClassificationSensitivityTexture ClassificationRobust Adaptive Median Binary Pattern for noisy texture classification and retrieval
Texture is an important cue for different computer vision tasks and applications. Local Binary Pattern (LBP) is considered one of the best yet efficient texture descriptors. However, LBP has some notable limitations, mos…
ClassificationGeneral ClassificationRetrievalTexture ClassificationDeveloping a gender classification approach in human face images using modified local binary patterns and tani-moto based nearest neighbor algorithm
Human identification is a much attention problem in computer vision. Gender classification plays an important role in human identification as preprocess step. So far, various methods have been proposed to solve this prob…
CPUGender ClassificationGeneral ClassificationSensitivityGradient-based Bit Encoding Optimization for Noise-Robust Binary Memristive Crossbar
Binary memristive crossbars have gained huge attention as an energy-efficient deep learning hardware accelerator. Nonetheless, they suffer from various noises due to the analog nature of the crossbars. To overcome such l…
Noise Stability of Transformer Models
Understanding simplicity biases in deep learning offers a promising path toward developing reliable AI. A common metric for this, inspired by Boolean function analysis, is average sensitivity, which captures a model's ro…