1. Deep Learning with Python

2. 파이썬 (python) 이란 ? 1991 년 Guido van Rossum 이 발표한 인터프리터 언어 Google 의 3 대 개발언어 (C/C++, Java, Python)

3. 파이썬의 특징 가독성 풍부한 라이브러리 접착성 무료 유니코드

4. 파이썬의 종류 Cpython C 로 작성된 인터프리터 Jython 자바 가상 머신용 인터프리터 IronPhthon.Net 과 Mono 용 인터프리터. C# 으로 구현됨 PyPy 파이썬으로 작성된 파이썬 인터프리터

5. 설치 및 개발환경 http://www.python.org/downloads

6. 파이썬 커맨드라인

7. 파이썬 IDLE

8. 자료형 - 수치

9. 자료형 - 문자열

10. 자료형 – List, Set, Tuple, Dictionary

11. Shallow/Deep Copy

12. Function

13. Modules and Packages Python modules “package program code and data for reuse.” (Lutz) –Similar to library in C, package in Java. Python packages are hierarchical modules (i.e., modules that contain other modules). Three commands for accessing modules: 1.import 2.from…import 3.reload

14. Modules and Packages: import The import command loads a module: # Load the regular expression module >>> import re To access the contents of a module, use dotted names: # Use the search method from the re module >>> re.search(‘\w+’, str) To list the contents of a module, use dir: >>> dir(re) [‘DOTALL’, ‘I’, ‘IGNORECASE’,…]

15. Modules and Packages from…import The from…import command loads individual functions and objects from a module: # Load the search function from the re module >>> from re import search Once an individual function or object is loaded with from…import, it can be used directly: # Use the search method from the re module >>> search (‘\w+’, str)

16. Import vs. from…import Import Keeps module functions separate from user functions. Requires the use of dotted names. Works with reload. from…import Puts module functions and user functions together. More convenient names. Does not work with reload.

17. Modules and Packages: reload If you edit a module, you must use the reload command before the changes become visible in Python: >>> import mymodule... >>> reload (mymodule) The reload command only affects modules that have been loaded with import ; it does not update individual functions and objects loaded with from...import.

18. NumPy Fundamental package for scientific computing with Python It contains among other things: a powerful N-dimensional array object sophisticated (broadcasting) functions tools for integrating C/C++ and Fortran code useful linear algebra, Fourier transform, and random number capabilities

19. NumPy: Functions & Attributes

20. NumPy: N-dimensional array object

21. 파이썬과 자연언어처리 Python is a great language for NLP: Simple Easy to debug: Exceptions Interpreted language Easy to structure Modules Object oriented programming Powerful string manipulation

22. Introduction to NLTK The Natural Language Toolkit (NLTK) provides: Basic classes for representing data relevant to natural language processing. Standard interfaces for performing tasks, such as tokenization, tagging, and parsing. Standard implementations of each task, which can be combined to solve complex problems.

23. NLTK: Example Modules nltk.token : processing individual elements of text, such as words or sentences. nltk.probability : modeling frequency distributions and probabilistic systems. nltk.tagger : tagging tokens with supplemental information, such as parts of speech or wordnet sense tags. nltk.parser : high-level interface for parsing texts. nltk.chartparser : a chart-based implementation of the parser interface. nltk.chunkparser : a regular-expression based surface parser.

24. NLTK: Top-Level Organization NLTK is organized as a flat hierarchy of packages and modules. Each module provides the tools necessary to address a specific task Modules contain two types of classes: Data-oriented classes are used to represent information relevant to natural language processing. Task-oriented classes encapsulate the resources and methods needed to perform a specific task.

25. Installing NLTK 32-bit binary installation Install Python: http://www.python.org/download/releases/3.4.1/ (avoid the 64-bit versions) Install Numpy (optional): http://sourceforge.net/projects/numpy/files/NumPy/1.8.1/numpy-1.8.1-win32-superpack- python3.4.exe Install NLTK: http://pypi.python.org/pypi/nltk Test installation: Start>Python34, then type import nltk

26. Installing NLTK Data

27. NLTK Corpora

28. NLTK Book

29. Simple Statistics

30. NLP Pipeline

31. Using a Tagger

32. Supervised Classification

33. Gender Identification

34. Gender Identification(cont.)

35. WordNet

36. Semantic Similarity

37. Theano Python library that allows you to define, optimize, and evaluate mathematical expressions involving multi-dimensional arrays efficiently Easy parallelization: CPU or GPU Speed optimization Deep learning tutorial codes Good maintenance A great user group

38. Requirements Linux, Mac OS X or Windows operating system Python >= 2.6 NumPy >= 1.6.2 SciPy >= 0.11 A BLAS installation (with Level 3 functionality)

39. Easy Installation of an Optimized Theano on Current Ubuntu For Ubuntu 11.10 through 14.04: sudo apt-get install python-numpy python-scipy python-dev python-pip python-nose g++ libopenblas-dev git sudo pip install Theano For Ubuntu 11.04: sudo apt-get install python-numpy python-scipy python-dev python-pip python-nose g++ git libatlas3gf-base libatlas-dev sudo pip install Theano

40. Test the newly installed packages NumPy (~30s): python -c "import numpy; numpy.test()“ SciPy (~1m): python -c "import scipy; scipy.test()“ Theano (~30m): python -c "import theano; theano.test()"

41. Adding two Scalars >>> import theano.tensor as T >>> x = T.dscalar('x') >>> y = T.dscalar('y') >>> z = x + y >>> z.eval({x : 16.3, y : 12.1}) array(28.4)

42. Adding two Matrices >>> x = T.dmatrix('x') >>> y = T.dmatrix('y') >>> z = x + y >>> f = function([x, y], z) >>> f([[1, 2], [3, 4]], [[10, 20], [30, 40]]) array([[ 11., 22.], [ 33., 44.]])

43. Logistic Function >>> x = T.dmatrix('x') >>> s = 1 / (1 + T.exp(-x)) >>> logistic = function([x], s) >>> logistic([[0, 1], [-1, -2]]) array([[ 0.5, 0.73105858], [ 0.26894142, 0.11920292]])

44. Restricted Boltzmann Machine

45. RBM in Theamo class RBM(object): """Restricted Boltzmann Machine (RBM) """ def __init__( self, input=None, n_visible=784, n_hidden=500, W=None, hbias=None, vbias=None, numpy_rng=None, theano_rng=None ):

46. Generative Training

47. Contrastive Divergence

48. Bayesian network(=Belief network) probabilistic graphical model represents a set of random variables and their conditional dependencies via a directed acyclic graph

49. Layer Stacking

50. Deep Learning for WSD WSD(Word Sense Disambiguation) 둘 이상의 의미로 사용되는 어휘가 문맥에서 어떤 의미로 사용되었는지 를 구분하는 작업 기계번역 / 정보검색 등 자연언어처리 응용시스템의 성능을 좌우함 차에서 내리자 내리는 눈 때문에 모두 건물 안으로 뛰어갔다.

51. 세종 의미분석 말뭉치

52. Naïve Bayes for WSD Bayes’ Rule s k : 중의성 어휘 s 의 의미 c : 중의성 어휘 s 의 주변 문맥 어휘

53. SVM for WSD

54. Word2Vec

55. Word2Vec Install Download the code: svn checkout http://word2vec.googlecode.com/svn/trunk/http://word2vec.googlecode.com/svn/trunk/ Run 'make' to compile word2vec tool Run the demo scripts:./demo-word.sh and./demo-phrases.sh For questions about the toolkit, see http://groups.google.com/group/word2vec-toolkithttp://groups.google.com/group/word2vec-toolkit Download the code: svn checkout http://word2vec.googlecode.com/svn/trunk/http://word2vec.googlecode.com/svn/trunk/ Run 'make' to compile word2vec tool Run the demo scripts:./demo-word.sh and./demo- phrases.sh For questions about the toolkit, see http://groups.google.com/group/word2vec-toolkithttp://groups.google.com/group/word2vec-toolkit

56. Vector Representation in Word2Vec >>> model = Word2Vec(sentences, size=200) # default value is 100 >>> model.most_similar(positive=['woman', 'king'], negative=['man'], topn=1) [('queen', 0.50882536)] >>> model.doesnt_match("breakfast cereal dinner lunch".split()) 'cereal' >>> model.similarity('woman', 'man') 0.73723527 >>> model['computer'] # raw NumPy vector of a word array([-0.00449447, -0.00310097, 0.02421786,...], dtype=float32)