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

大型語言模型

Large Language Models

學期
113-1
學分
3 學分
當期課號
535104
永久課號
EEEE30045
開課單位
電機工程學系
授課教師
簡仁宗、梁伯嵩
校區
光復
類別
選修
上課時間表
週五
5
13:20–14:10
大型語言模型
ED103
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

Large language models (LLMs) offers a unique opportunity to peek behind the curtains of the groundbreaking advancements in generative artificial intelligence (GAI). By delving into these developments, you will understand how language models are evolved and exploited to deploy over various domains. This course will address how LLMs work under the hood, tearing the lid off the GAI black box. LLMs provide a platform to explore how machines can comprehend, generate, and manipulate language in ways that mimic human cognition. This course focuses on the fundamentals in computation theories, architectures and practices for LLMs, and highlights the academic and industrial advances in the extended models and applications.

先修科目

Calculus, Linear Algebra, Probability and Statistics

教學方式

Teaching materials, codes and datasets will be provided. Teacher assistants will be available at PM19:00-20:00 in week days. Appointments are required. You are encouraged to use online discussion function in E3. TAs will promptly reply your questions.

評分方式

Temporary Policy: Homework (or Task Competition) (60%), Final Project (40%), Class Attendance (+10%)

課程大綱
週次計畫
週次主題
第 1 週Feedforward & Convolutional Neural Networks
第 2 週Regularization for Optimization in Deep Learning
第 3 週Recurrent Neural Network & Sequential Learning
第 4 週N-Gram Language Models & Topic-Based Language Models
第 5 週RNN Language Models & Language Understanding
第 6 週Attention Networks & Transformers
第 7 週BERT Encoder & GPT Decoder
第 8 週Retrieval, Augmentation & Generation
第 9 週Generation with Prompting Strategies
第 10 週LLMs with GPT, LLaMA & Breeze
第 11 週AI Computing Architecture for LLM
第 12 週DaVinci GAI Platform & Applications
第 13 週LLM Model Trends and Generative AI
第 14 週Final Presentation
第 15 週Final Presentation
第 16 週Final Presentation
教科書

1. Lecture Notes and Slides 2. I. Goodfellow and Y. Bengio and A. Courville, Deep Learning, The MIT Press, 2016. 3. S. Watanabe and J.-T. Chien, Bayesian Speech and Language Processing, Cambridge University Press, 2015.

Office Hours
地點
ED708
時間
PM18:00-18:30 on Monday. Appointments are required.
聯絡方式
jtchien@nycu.edu.tw