Uncertainty Propagation in Convolutional Neural Networks: Technical Report
In this technical report we study the problem of propagation of uncertainty (in terms of variances of given uni-variate normal random variables) through typical building blocks of a Convolutional Neural Network (CNN). These include layers that perform linear operations, such as 2D convolutions, fully-connected, and average pooling layers, as well as layers that act non-linearly on their input, such as the Rectified Linear Unit (ReLU). Finally, we discuss the sigmoid function, for which we give approximations of its first- and second-order moments, as well as the binary cross-entropy loss function, for which we approximate its expected value under normal random inputs.
Code (2)
Methods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Uncertainty Propagation in LLM-Based Systems
Uncertainty in large language model (LLM)-based systems is often studied at the level of a single model output, yet deployed LLM applications are compound systems in which uncertainty is transformed and reused across mod…
Deep learning: Technical introduction
This note presents in a technical though hopefully pedagogical way the three most common forms of neural network architectures: Feedforward, Convolutional and Recurrent. For each network, their fundamental building block…
Deep LearningTowards Propagation Uncertainty: Edge-enhanced Bayesian Graph Convolutional Networks for Rumor Detection
Detecting rumors on social media is a very critical task with significant implications to the economy, public health, etc. Previous works generally capture effective features from texts and the propagation structure. How…
Feedback-prop: Convolutional Neural Network Inference under Partial Evidence
We propose an inference procedure for deep convolutional neural networks (CNNs) when partial evidence is available. Our method consists of a general feedback-based propagation approach (feedback-prop) that boosts the pre…
Prediction of Ultrasonic Guided Wave Propagation in Solid-fluid and their Interface under Uncertainty using Machine Learning
Structural health monitoring (SHM) systems use the non-destructive testing principle for damage identification. As part of SHM, the propagation of ultrasonic guided waves (UGWs) is tracked and analyzed for the changes in…
Gaussian ProcessesStructural Health Monitoring