• 沒有找到結果。

Applied Deep Learning - Syllabus National Taiwan University, 2016 Fall Semester Instructor Information

N/A
N/A
Protected

Academic year: 2022

Share "Applied Deep Learning - Syllabus National Taiwan University, 2016 Fall Semester Instructor Information"

Copied!
2
0
0

加載中.... (立即查看全文)

全文

(1)

Page 1

Applied Deep Learning - Syllabus

National Taiwan University, 2016 Fall Semester

Instructor Information

Instructor Email Lecture Location & Hours

Yun-Nung (Vivian) Chen 陳縕儂 [email protected] Thursday 9:10-12:10

General Information

Description

Learning the basic theory of deep learning and how to apply to various applications Expectations and Goals

The students are expected to understand 1) how deep learning works

2) how to frame tasks into deep learning problems

3) how to use deep learning toolkits to implement the designed models, and 4) when and why specific deep learning techniques work for specific problems.

Assignments & Project

5 assignments, 1 group final project, 1 write-up report

Pre-requisites

Required Coding Skills

 Proficiency in Python; All assignments will in Python.

Required Courses

 College Calculus

 Linear Algebra

 Probability

 Machine Learning (preferred but optional)

 Statistics (preferred but optional)

(2)

Page 2

Course Schedule

Week Topic Reading Assignment

1 (09/15/2016) 中秋假期 2 (09/22/2016) Introduction 3 (09/29/2016) Neural Networks 4 (10/06/2016) Backpropagation

5 (10/13/2016) Word Representation Word Embedding

6 (10/20/2016) Sequential Modeling

7 (10/27/2016) Recursive Neural Networks Sentiment Analysis 8 (11/03/2016) Convolutional Neural Networks

9 (11/10/2016) Recurrent Neural Networks

10 (11/17/2016) Gated Mechanism Natural Language Understanding

11 (11/24/2016) TBA

12 (12/01/2016) Attention Mechanism Language Generation

13 (12/08/2016) Representation Learning Multi-Task Learning 14 (12/15/2016) TBA

15 (12/22/2016) Deep Reinforcement Learning Game Playing 16 (12/29/2016) Deep Reinforcement Learning

17 (01/05/2017) TBA

18 (01/12/2017) Final Project Presentation

Assignment Schedule

Release Date Due Date Subject Time

10/13/2016 10/27/2016 Word Embedding 2 weeks

10/27/2016 11/17/2016 Sentiment Analysis 3 weeks

11/17/2016 12/01/2016 Natural Language Understanding 2 weeks

12/01/2016 12/22/2016 Language Generation 3 weeks

12/22/2016 01/05/2017 Game Playing 2 weeks

參考文獻

相關文件

○ Value function: how good is each state and/or action. ○ Policy: agent’s

• User goal: Two tickets for “the witch” tomorrow 9:30 PM at regal meridian 16, Seattle. E2E Task-Completion Bot (TC-Bot) (Li et

 End-to-end reinforcement learning dialogue system (Li et al., 2017; Zhao and Eskenazi, 2016)?.  No specific goal, focus on

automatic pattern feature extraction from layers of neurons with backprop for GD/SGD. Lecture 3: Optimization in Deep Learning Difficulty of Deep

Most existing machine learning algorithms are designed by assuming that data can be easily accessed.. Therefore, the same data may be accessed

As for real-time polyp detection, our YOLOv4 transfer learning model achieves high quality, and convincing object detection results obviously.. Our deep learning polyp

MR CLEAN: A Randomized Trial of Intra-arterial Treatment for Acute Ischemic Stroke. • Multicenter Randomized Clinical trial of Endovascular treatment for Acute ischemic stroke in

- Effective use of a variety of texts (e.g. information texts) to encourage deep reading, connect students’ learning experience and broaden their knowledge base. -