A5059285731- Advanced Statistical Methods and Models
- Galaxies: Formation, Evolution, Phenomena
- Astronomy and Astrophysical Research
- CCD and CMOS Imaging Sensors
- Astronomical Observations and Instrumentation
- Statistical and numerical algorithms
- Gamma-ray bursts and supernovae
- Anomaly Detection Techniques and Applications
- Water Systems and Optimization
- Fire Detection and Safety Systems
University of California, Los Angeles
2024
Chengdu University of Technology
2023
UCLA Health
2021
Abstract We present results exploring the role that probabilistic deep learning models can play in cosmology from large-scale astronomical surveys through photometric redshift (photo- z ) estimation. Photo- uncertainty estimates are critical for science goals of upcoming such as Legacy Survey Space and Time (LSST); however, common machine methods typically provide only point lack uncertainties on predictions. turn to Bayesian neural networks (BNNs) a promising way accurate predictions values...
We present results exploring the role that probabilistic deep learning models can play in cosmology from large-scale astronomical surveys through photometric redshift (photo-z) estimation. Photo-z uncertainty estimates are critical for science goals of upcoming such as LSST, however common machine methods typically provide only point and lack uncertainties on predictions. turn to Bayesian neural networks (BNNs) a promising way accurate predictions values with estimates. have compiled galaxy...
The safe operation of gas pipelines in urban, industrial, agricultural, and other areas still faces risks challenges. pipeline leak detection method is aimed at improving the safety operations various fields reducing losses caused by leaks. This utilizes highly sensitive microphones to collect real-time sound signals environments uses Mel-scale Frequency Cepstral Coefficients (MFCC) algorithm extract features from collected signals. Then, a convolutional neural network used identify whether...
We present results exploring the role that probabilistic deep learning models can play in cosmology from large scale astronomical surveys through estimating distances to galaxies (redshifts) photometry. Due massive of data coming these new and upcoming sky surveys, machine techniques using galaxy photometry are increasingly adopted predict galactic redshifts which important for inferring cosmological parameters such as nature dark energy. Associated uncertainty estimates also critical...