課程說明
不確定性、不確定性傳播、貝式推論、感測器融合、時間序列、高斯過程、將科學/使用者知識整合到機器學習、用於微分方程的神經網路、機率深度學習、序列決策。個案研究將取自生醫、自駕車、感測器與訊號處理等各領域。
原文參考文本
Uncertainty, uncertainty propagation, Bayesian inference, sensor fusion, time series, Gaussian processes, integrating scientific/user knowledge into machine learning, neural networks for differential equations, probabilistic deep learning, sequential decision making. Case studies will be drawn from various fields including biomedical, autonomous vehicles, sensors, and signal processing.
來源與參考
保留日期與來源以協助你核實資料。為便於閱讀提供譯文；官方來源為條件與要求的參照。
來源參考 : https://calendar.carleton.ca/grad/courses/COMP/