<?xml version="1.0" encoding="UTF-8"?>
<rss version="2.0">
  <channel>
    <title>MyCloud</title>
    <link>https://swalloow.tistory.com/</link>
    <description>지식을 담는 블로그 :D</description>
    <language>ko</language>
    <pubDate>Sun, 21 Jun 2026 02:27:20 +0900</pubDate>
    <generator>TISTORY</generator>
    <ttl>100</ttl>
    <managingEditor>Swalloow</managingEditor>
    <image>
      <title>MyCloud</title>
      <url>https://t1.daumcdn.net/cfile/tistory/2236243856A71EC80C</url>
      <link>https://swalloow.tistory.com</link>
    </image>
    <item>
      <title>블로그 이전</title>
      <link>https://swalloow.tistory.com/105</link>
      <description>jekyll 블로그로 이전했습니다.주소는&amp;nbsp;http://swalloow.github.io&amp;nbsp;입니다.</description>
      <category>About</category>
      <author>Swalloow</author>
      <guid isPermaLink="true">https://swalloow.tistory.com/105</guid>
      <comments>https://swalloow.tistory.com/105#entry105comment</comments>
      <pubDate>Sun, 29 Jan 2017 18:31:03 +0900</pubDate>
    </item>
    <item>
      <title>[Git] 로컬 브랜치와 충돌로 인해 pull 오류 발생 시 대처법</title>
      <link>https://swalloow.tistory.com/104</link>
      <description>로컬 브랜치와 충돌로 인해 pull 오류 발생 시 대처법error: Your local changes to the following files would be overwritten by merge: ----Please commit your changes or stash them before you merge. Aborting로컬 브랜치와 충돌로 인해 pull이 이루어지지 않는 경우가 빈번합니다.이에 대한 해결 방법으로 2가지 정도가 있습니다.해결 방법 ..</description>
      <category>Project/OpenSource</category>
      <category>Aborting</category>
      <category>git</category>
      <category>Merge</category>
      <category>Pull</category>
      <category>Reset</category>
      <category>stash</category>
      <category>되돌리기</category>
      <category>브랜치</category>
      <category>오류</category>
      <category>충돌</category>
      <category>해결방법</category>
      <author>Swalloow</author>
      <guid isPermaLink="true">https://swalloow.tistory.com/104</guid>
      <comments>https://swalloow.tistory.com/104#entry104comment</comments>
      <pubDate>Fri, 13 Jan 2017 14:04:00 +0900</pubDate>
    </item>
    <item>
      <title>SK Tech Planet 2016 후기</title>
      <link>https://swalloow.tistory.com/101</link>
      <description>코엑스에서 열린 SK Tech Planet 2016에 다녀왔습니다 !늦었지만 들었던 세션을 중심으로 몇 가지 내용을 정리하고자 합니다.매 시간마다 세&amp;nbsp;개의 트랙 중 하나를 선택해서 들을 수 있었는데,저는 주로 머신러닝, 딥러닝, 자연어처리에 대한 세션을 들었습니다....1. Apache Spark은 어떻게 가장 활발한 빅데이터 프로젝트가 되었나&amp;nbsp;최근 5년 사이의 오픈소스 프로젝트 흐름을 그물망 형태로 보여주신 것이 인상적이었습니다.지난..</description>
      <category>About</category>
      <category>2016</category>
      <category>Kaggle</category>
      <category>Planet</category>
      <category>sk</category>
      <category>Tech</category>
      <category>머신러닝</category>
      <category>발표자료</category>
      <category>세션</category>
      <category>자연어처리</category>
      <category>정리</category>
      <category>챗봇</category>
      <category>컨퍼런스</category>
      <category>후기</category>
      <author>Swalloow</author>
      <guid isPermaLink="true">https://swalloow.tistory.com/101</guid>
      <comments>https://swalloow.tistory.com/101#entry101comment</comments>
      <pubDate>Sun, 23 Oct 2016 16:14:44 +0900</pubDate>
    </item>
    <item>
      <title>한국어 자연어처리 관련 라이브러리 정리</title>
      <link>https://swalloow.tistory.com/100</link>
      <description>


Natural Language Processing








파이썬은 한국어 자연어처리를 위해 다양한 라이브러리가 존재합니다.그 중에서 자주 사용하며 필수적인 몇 가지 라이브러리에 대해 소개하겠습니다.1. KoNLPyKoNLPy는 한국어 형태소 분석기로써 Twitter, Komoran, Mecab 등 다양한형태소 분석기를 모듈화하여 내장하고 있다는 장점이 있습니다.또한, 문서화가 잘되어 있어 사용하기 편리합니다!링크 :&amp;nbsp;http://k..</description>
      <category>Knowledge/Natural Language</category>
      <category>gensim</category>
      <category>hangul</category>
      <category>hangulize</category>
      <category>hanja</category>
      <category>Konlpy</category>
      <category>MeCab</category>
      <category>NLP</category>
      <category>라이브러리</category>
      <category>자연어처리</category>
      <category>정리</category>
      <category>파이썬</category>
      <category>패키지</category>
      <category>한국어</category>
      <author>Swalloow</author>
      <guid isPermaLink="true">https://swalloow.tistory.com/100</guid>
      <comments>https://swalloow.tistory.com/100#entry100comment</comments>
      <pubDate>Sun, 16 Oct 2016 03:14:25 +0900</pubDate>
    </item>
    <item>
      <title>소프트웨어 마에스트로 7기 합격 후기</title>
      <link>https://swalloow.tistory.com/78</link>
      <description>얼마전 소프트웨어 마에스트로 서류, 면접을 보았는데,다른 분들의 블로그를 통해 정말 많은 도움이 되었습니다!그래서 저도 후기를 남기기로 결정.소프트웨어 마에스트로 7기 지원 후기먼저 서류전형은&amp;nbsp;진행했던 프로젝트를 쓰는 비중이 가장 높았습니다.어떤 프로젝트인지, 어려웠던 점, 해결방법을 중심으로 적어야 합니다.그리고 소스코드를 제출해야하기 때문에 GItHub을 통해&amp;nbsp;오픈소스로 관리하는 것을 추천합니다.이외에도 소마에서 진행하려는 프로젝트..</description>
      <category>About</category>
      <category>7기</category>
      <category>SW maestro</category>
      <category>마에스트로</category>
      <category>면접</category>
      <category>서류</category>
      <category>소프트웨어</category>
      <category>인적성</category>
      <category>지원</category>
      <category>질문</category>
      <category>코딩테스트</category>
      <category>프로젝트</category>
      <category>합격</category>
      <category>후기</category>
      <author>Swalloow</author>
      <guid isPermaLink="true">https://swalloow.tistory.com/78</guid>
      <comments>https://swalloow.tistory.com/78#entry78comment</comments>
      <pubDate>Fri, 2 Sep 2016 10:55:01 +0900</pubDate>
    </item>
    <item>
      <title>[Git] 자주 사용하는 명령어 정리</title>
      <link>https://swalloow.tistory.com/98</link>
      <description>


Git command








1. 저장소 관련 명령어// 로컬 저장소 복제git clone 사용자명@호스트:/원격/저장소/경로// 추가와 커밋git statusgit add *git commit -m &quot;contents&quot;git push origin master// 원격 서버로 발행git remote add origin &amp;lt;remote server&amp;gt;2. 브랜치 관련 명령어// 브랜치 만들기git checkout -b branch_nam..</description>
      <category>Project/OpenSource</category>
      <category>bash</category>
      <category>checkout</category>
      <category>commit</category>
      <category>git</category>
      <category>Merge</category>
      <category>stash</category>
      <category>되돌리기</category>
      <category>명령어</category>
      <category>브랜치</category>
      <category>사용하는</category>
      <category>자주</category>
      <category>저장소</category>
      <category>정리</category>
      <category>충돌</category>
      <category>취소</category>
      <category>커밋</category>
      <author>Swalloow</author>
      <guid isPermaLink="true">https://swalloow.tistory.com/98</guid>
      <comments>https://swalloow.tistory.com/98#entry98comment</comments>
      <pubDate>Wed, 10 Aug 2016 03:22:57 +0900</pubDate>
    </item>
    <item>
      <title>[NumPy] 서로 다른 Matrix를 합치는 방법</title>
      <link>https://swalloow.tistory.com/97</link>
      <description>


Numpy - Sparse Matrix








TfidfVectorizer에&amp;nbsp;bigram을 사용하여&amp;nbsp;변환된 3068x23466 sparse matrix에&amp;nbsp;unigram을 이어붙이고 싶을 때,여러&amp;nbsp;개의 서로 다른 sparse matrix를 이어붙이는 방법에 대해 적어두려고 합니다.1. np.c_import numpy as np# matrix a, bnp.c_[a, b]* sparse matrix의 경우 'C..</description>
      <category>Programming/Python</category>
      <category>hstack</category>
      <category>numpy</category>
      <category>scipy</category>
      <category>sparse matrix</category>
      <category>vstack</category>
      <category>방법</category>
      <category>병합</category>
      <category>파이썬</category>
      <author>Swalloow</author>
      <guid isPermaLink="true">https://swalloow.tistory.com/97</guid>
      <comments>https://swalloow.tistory.com/97#entry97comment</comments>
      <pubDate>Wed, 10 Aug 2016 03:21:34 +0900</pubDate>
    </item>
    <item>
      <title>[Coursera] 머신러닝 4주차 강의정리</title>
      <link>https://swalloow.tistory.com/96</link>
      <description>


Neural Networks: Motivations








이전에 Logistic Regression을 통해 Quadratic model을 분류할 수 있게 되었습니다.하지만 feature가 2~3개가 아니라 10만개가 넘는다면? Logistic Regression으로 성능을 내기 힘들게 됩니다.대표적인 예시가&amp;nbsp;컴퓨터 비전 분야입니다.예를 들어, 사진을 주고 이것이 자동차인지 아닌지 컴퓨터가 구분하는 것입니다.사람이 보기에 자동차의 ..</description>
      <category>Knowledge/Machine Learning</category>
      <category>bias</category>
      <category>Coursera</category>
      <category>Neural network</category>
      <category>강의</category>
      <category>개요</category>
      <category>뉴럴네트워크</category>
      <category>머신러닝</category>
      <category>시그모이드</category>
      <category>신경망</category>
      <category>알고리즘</category>
      <category>인공신경망</category>
      <category>정리</category>
      <category>코세라</category>
      <author>Swalloow</author>
      <guid isPermaLink="true">https://swalloow.tistory.com/96</guid>
      <comments>https://swalloow.tistory.com/96#entry96comment</comments>
      <pubDate>Wed, 10 Aug 2016 03:19:21 +0900</pubDate>
    </item>
    <item>
      <title>머신러닝 회귀모델(Regression) 정리</title>
      <link>https://swalloow.tistory.com/95</link>
      <description>


Regression








Linear Regression, Logistic Regression, Softmax Regression에 관해 정리한 좋은 자료를 찾아서 공유합니다.출처 : TensorFlow KR - Deep NLP Study</description>
      <category>Knowledge/Machine Learning</category>
      <category>Linear</category>
      <category>Logistic</category>
      <category>regression</category>
      <category>Softmax</category>
      <category>머신러닝</category>
      <category>요약</category>
      <category>정리</category>
      <category>회귀</category>
      <author>Swalloow</author>
      <guid isPermaLink="true">https://swalloow.tistory.com/95</guid>
      <comments>https://swalloow.tistory.com/95#entry95comment</comments>
      <pubDate>Fri, 5 Aug 2016 03:19:00 +0900</pubDate>
    </item>
    <item>
      <title>[Coursera] 머신러닝 3주차 강의정리</title>
      <link>https://swalloow.tistory.com/94</link>
      <description>


Logistic&amp;nbsp;Regression








Logistic Regression이란, 우리말로 로지스틱 회귀라고 하는데,&amp;nbsp;역시 전혀 감이 안옵니다.간단히 설명하자면, Logistic Regression은 분류(Classification)를 위한 예측모델입니다.특히 Negative 또는&amp;nbsp;Positive, 즉 0 또는 1로 정의되는 이항형 문제에서 사용됩니다.Anderw Ng이 들었던 예시는 다음과 같습니다.어떤 암 환..</description>
      <category>Knowledge/Machine Learning</category>
      <category>cost function</category>
      <category>Coursera</category>
      <category>Logistic</category>
      <category>regression</category>
      <category>sigmoid</category>
      <category>강의</category>
      <category>로지스틱</category>
      <category>머신러닝</category>
      <category>시그모이드 함수</category>
      <category>앤드류응</category>
      <category>정리</category>
      <category>회귀</category>
      <author>Swalloow</author>
      <guid isPermaLink="true">https://swalloow.tistory.com/94</guid>
      <comments>https://swalloow.tistory.com/94#entry94comment</comments>
      <pubDate>Fri, 5 Aug 2016 02:06:20 +0900</pubDate>
    </item>
  </channel>
</rss>