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

可信任節能生成式AI

Trustworthy Green Generative AI

學期
114-2
學分
3 學分
當期課號
639011
永久課號
AICA30041
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
可信任節能生成式AI
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

This course (Trustworthy Green Generative AI) consists of two parts: trustworthy machine learning algorithms and efficient algorithm development and implementation. In the first part, we will discuss algorithms that provide reliable confidence scores for their predictions in a systematic and analytical manner, including Gaussian Process regression and classification. In the second part, we will explore efficient accelerated computation, covering training, fine-tuning, and inference of large language models on consumer-grade computers.

先修科目

Basic machine learning concepts, such as overfitting, gradient descent, neural networks etc..

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: Advanced Topics, MIT Press, 2022, URL = https://probml.github.io/pml-book/book2.html 3. Up to date AI papers

評分方式

Homework: 30% Project: 50% Attendance: 20% 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. GPs help us train large models with fewer expensive experiments. (Coding and Report) Ex6. Uncertainty quantification vis attention chain (Coding and report) Ex7. Response Uncertainty and Probe Modeling: Two Sides of the Same Coin in LLM Interpretability (Coding and Report) Ex8. Linear transformer (Coding and 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 Data Generation Concepts
第 4 週Bayesian inference, Gaussian distribution and Gaussian process
第 5 週Understanding kernels and similarity metrics
第 6 週Application: GPs help us train large models with fewer expensive experiments.
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
第 12 週uncertainty quantification vis attention chain
第 13 週Response Uncertainty and Probe Modeling: Two Sides of the Same Coin in LLM Interpretability
第 14 週Linear Transformer and delta Rules
第 15 週Low rank computation: LoRA and Galore
第 16 週Term project report
教科書

No textbook for this course. Pioneering and contemporary papers will be discussed in the class.

Office Hours
地點
in the class
時間
By appointment or after class every week.
聯絡方式
machingwen@nycu.edu.tw