Flying By ML -- CNN Inversion of Affine Transforms
This paper describes a machine learning method to automate reading of cockpit gauges, using a CNN to invert affine transformations and deduce aircraft states from instrument images. Validated with synthetic images of a turn-and-bank indicator, this research introduces methods such as generating datasets from a single image, the 'Clean Training Principle' for optimal noise-free training, and CNN interpolation for continuous value predictions from categorical data. It also offers insights into hyperparameter optimization and ML system software engineering.
Code (0)
등록된 구현이 없습니다.
Tasks
Hyperparameter OptimizationSimilar Papers 제목 키워드 기반
A note on the Artstein-Avidan-Milman's generalized Legendre transforms
Artstein-Avidan and Milman [Annals of mathematics (2009), (169):661-674] characterized invertible reverse-ordering transforms on the space of lower semi-continuous extended real-valued convex functions as affine deformat…
Affine Variational Autoencoders: An Efficient Approach for Improving Generalization and Robustness to Distribution Shift
In this study, we propose the Affine Variational Autoencoder (AVAE), a variant of Variational Autoencoder (VAE) designed to improve robustness by overcoming the inability of VAEs to generalize to distributional shifts in…
FormAnalytic Bijections for Smooth and Interpretable Normalizing Flows
A key challenge in normalizing flows is finding expressive invertible scalar bijections. Existing approaches face trade-offs: affine transformations are smooth and analytically invertible but lack expressivity; monotonic…
Stable Inversion of Piecewise Affine Systems with Application to Feedforward and Iterative Learning Control
Model inversion is a fundamental technique in feedforward control. Unstable inverse models present a challenge in that useful feedforward control trajectories cannot be generated by directly propagating them. Stable inve…
Affine Transformation Edited and Refined Deep Neural Network for Quantitative Susceptibility Mapping
Deep neural networks have demonstrated great potential in solving dipole inversion for Quantitative Susceptibility Mapping (QSM). However, the performances of most existing deep learning methods drastically degrade with …