¿¬¼¼´ëÇб³ °æ¿µ´ëÇÐ BK21Plus

¸ÞÀθ޴º

ÄÜÅÙÃ÷ ¿µ¿ª

Data Science for Start-up (University of Texas, Pf. Gene moo Lee)
µî·ÏÀÏ: 2016-09-08  |  Á¶È¸¼ö: 1,164

 

ÀϽÃ: 2016³â 7¿ù 12, 18, 21ÀÏ (ÃÑ 3ÀÏ) 13:00-18:00

Àå¼Ò: °æ¿µ°ü B208È£(ÄÄÇ»ÅÍ·¦)

 

Course Objective:
This class is to introduce text mining and deep learning for people without extensive programming background. The class will cover both the concepts and the practices. For practices, we will use Python and Scala. Python is one of the most popular programming languages in the data science community thanks to its readability and accessibility. We will use Python for text preprocessing step. Then, using a functional language Scala, we will learn Stanford Topic Model Toolkit to conduct topic modeling tasks. Finally, as an introduction to deep learning, we will use TensorFlow to conduct basic image processing tasks.

Course Plans:

Time

#

Content

Tuesday, July 12th

13:00~13:50

1

Introduction & Icebreaking

14:00~14:50

2

Python – Data Types /   Imperative Programming

15:00~15:50

3

Text Input Output –   CSV, JSON, Pickle

16:00~16:50

4

Container: Dictionary,   Set

17:00~17:50

5

Lab 1: Analyze text files

Monday, July 18th  

13:00~13:50

6

Text data collection -   Web Scraping with BeautifulSoup

14:00~14:50

7

Text preprocessing- NLTK, TextBlob, Stemming

15:00~15:50

8

Topic modeling –   Concept

16:00~16:50

9

Topic modeling – Linux,   SSH, Shell, screen

17:00~17:50

10

Topic modeling –   Stanford TMT

Lab2: Run LDA with TMT

Thursday,   July 21st

13:00~13:50

11

Recap of text mining

14:00~14:50

12

Deep learning – Concept

15:00~15:50

13

Showcase: Tumblr image   analysis

16:00~16:50

14

Deep learning – Lab   with TensorFlow

17:00~17:50

15

Deep learning – Lab MNIST

ÆäÀÌÁö ·Îµù À̹ÌÁö Ç¥½Ã

x
x