校際選修

115-1 選課時程

進行中

  • 初選第一階段 6/15/2026
  • 初選第二階段 6/22/2026
  • 校際選修 8/24/2026
  • 初選第三階段 8/31/2026
  • 開學後加退選 9/7/2026
  • 逾期加退選 9/21/2026
選課資源

深度概率機器學習

Deep Probabilistic Machine Learning

學期
112-2
學分
3 學分
當期課號
639102
永久課號
AICA30026
開課單位
智慧科學暨綠能學院
授課教師
馬清文
校區
歸仁
類別
選修
上課時間表
週二
5
13:20–14:10
深度概率機器學習
CM216
3 節連堂
6
14:20–15:10
7
15:30–16:20

* 根據陽明交大上課時間表所列

概述

Deep probabilistic machine learning is about making probabilistic predictions with deep neural networks, which can be appiled to generative AI sytems. This course focus on 1. providing reliable confidence scores for predictions in a systematic and analytical way, 2. generate probabilistic contents. The first part of this course covers Gaussian process regression, Gaussian process classifiers, deep Gaussian process classifiers and their applications, such as time series estimation and forecasting. We will study its financial applications. The second part of this course introduces some modern machine learning topics, especially generative AI systems, such as transformer networks, denoising diffusion, large language model, state space machines for sequence modeling etc.

先修科目

1. Basic machine learning concepts, such as overfitting, underlining, gradient descent, etc.. 2. Basics of probability theory, linear algebra, and multivariable calculus 3. Reasonably computer programming skills in Python/numpy

教學方式

Websites and reference books. 1. Hennig, P., 2020. Probabilistic Machine Learning. lecture course, University of Tübingen, URL = https://uni-tuebingen.de/en/180804 2. Kevin P. Murphy, Probabilistic Machine Learning: An introduction, MIT Press, 2022, URL = https://probml.github.io/pml-book/book1.html URL = https://probml.github.io/pml-book/book2.html

評分方式

Ex1. Basic Bayesian inference. (Coding) Ex2. Gaussian linear regression (Coding) Ex3. Gaussian process regression (Coding) Ex4. Integrating Gaussian process classifier and deep neural networks. (Coding) Ex5. Financial Application of Gaussian processes and Bayesian optimization (Coding and Report) Ex6. Integrating CNN and Gaussian process classifier. (Coding and report) Ex7. Transformer networks for object detection (Report) Ex8. Denoising Diffusion Models in computer vision (Report) Ex9. Large-Language Model (Report)

週次計畫
週次主題
第 1 週Course outline
第 2 週Reasoning under uncertainty Bayesian theorem
第 3 週Monte Carlo sampling
第 4 週Bayesian inference, Gaussian distribution and Gaussian process
第 5 週Understanding kernels and similarity metrics
第 6 週Example: Financial Application of Gaussian processes
第 7 週Gaussian process classification
第 8 週Generalized linear model and Exponential families
第 9 週Towards Bayesian Neural network: Last-layer Laplace approximation vs. deterministic uncertainty estimation
第 10 週Review and Report
第 11 週Probabilistic classifier integrating deep neural network and Gaussian process (I)
第 12 週Probabilistic classifier integrating deep neural network and Gaussian process (II)
第 13 週Transformers Architecture Attention vs. State Space Models
第 14 週Denoising Diffusion models
第 15 週Vision-Language Pre-training (CLIP) Concepts disentangle representation
第 16 週Term project report
教科書

No textbook for this course.

Office Hours
地點
on-line or 致遠樓 2樓R212)
時間
By appointment
聯絡方式
machingwen@nycu.edu.tw