Document (#40886)

Author
Maaten, L. van den
Hinton, G.
Title
Visualizing non-metric similarities in multiple maps
Source
Machine learning. 87(2012) no.1, S.33-55
Year
2012
Abstract
Techniques for multidimensional scaling visualize objects as points in a low-dimensional metric map. As a result, the visualizations are subject to the fundamental limitations of metric spaces. These limitations prevent multidimensional scaling from faithfully representing non-metric similarity data such as word associations or event co-occurrences. In particular, multidimensional scaling cannot faithfully represent intransitive pairwise similarities in a visualization, and it cannot faithfully visualize "central" objects. In this paper, we present an extension of a recently proposed multidimensional scaling technique called t-SNE. The extension aims to address the problems of traditional multidimensional scaling techniques when these techniques are used to visualize non-metric similarities. The new technique, called multiple maps t-SNE, alleviates these problems by constructing a collection of maps that reveal complementary structure in the similarity data. We apply multiple maps t-SNE to a large data set of word association data and to a data set of NIPS co-authorships, demonstrating its ability to successfully visualize non-metric similarities.
Content
Vgl. auch: https://lvdmaaten.github.io/tsne/.
Theme
Data Mining
Visualisierung
Object
tSNE

Similar documents (author)

  1. Hinton, F.: Dewey 17: a review (1966) 6.16
    6.163078 = sum of:
      6.163078 = weight(author_txt:hinton in 1721) [ClassicSimilarity], result of:
        6.163078 = fieldWeight in 1721, product of:
          1.0 = tf(freq=1.0), with freq of:
            1.0 = termFreq=1.0
          9.860925 = idf(docFreq=5, maxDocs=42306)
          0.625 = fieldNorm(doc=1721)
    
  2. Hinton, G.E.: Wie neuronale Netze aus Erfahrung lernen (1992) 6.16
    6.163078 = sum of:
      6.163078 = weight(author_txt:hinton in 7577) [ClassicSimilarity], result of:
        6.163078 = fieldWeight in 7577, product of:
          1.0 = tf(freq=1.0), with freq of:
            1.0 = termFreq=1.0
          9.860925 = idf(docFreq=5, maxDocs=42306)
          0.625 = fieldNorm(doc=7577)
    
  3. Fisher, K.E.; Durrance, J.C.; Hinton, M.B.: Information grounds and the use of need-based services by immigrants in Queens, New York: : a context-based, outcome evaluation approach (2004) 3.70
    3.697847 = sum of:
      3.697847 = weight(author_txt:hinton in 3248) [ClassicSimilarity], result of:
        3.697847 = fieldWeight in 3248, product of:
          1.0 = tf(freq=1.0), with freq of:
            1.0 = termFreq=1.0
          9.860925 = idf(docFreq=5, maxDocs=42306)
          0.375 = fieldNorm(doc=3248)
    
  4. Maaten, L. van den; Hinton, G.: Visualizing data using t-SNE (2008) 3.70
    3.697847 = sum of:
      3.697847 = weight(author_txt:hinton in 807) [ClassicSimilarity], result of:
        3.697847 = fieldWeight in 807, product of:
          1.0 = tf(freq=1.0), with freq of:
            1.0 = termFreq=1.0
          9.860925 = idf(docFreq=5, maxDocs=42306)
          0.375 = fieldNorm(doc=807)
    

Similar documents (content)

  1. Rorvig, M.: ¬A visual exploration of the orderliness of TREC relevance judgements (1999) 0.15
    0.15117137 = sum of:
      0.15117137 = product of:
        0.7558568 = sum of:
          0.05534411 = weight(abstract_txt:visualizations in 4769) [ClassicSimilarity], result of:
            0.05534411 = score(doc=4769,freq=1.0), product of:
              0.08895303 = queryWeight, product of:
                1.0031103 = boost
                7.9638047 = idf(docFreq=39, maxDocs=42306)
                0.011135032 = queryNorm
              0.62217224 = fieldWeight in 4769, product of:
                1.0 = tf(freq=1.0), with freq of:
                  1.0 = termFreq=1.0
                7.9638047 = idf(docFreq=39, maxDocs=42306)
                0.078125 = fieldNorm(doc=4769)
          0.011046048 = weight(abstract_txt:these in 4769) [ClassicSimilarity], result of:
            0.011046048 = score(doc=4769,freq=1.0), product of:
              0.043815207 = queryWeight, product of:
                1.2193863 = boost
                3.2269485 = idf(docFreq=4562, maxDocs=42306)
                0.011135032 = queryNorm
              0.25210536 = fieldWeight in 4769, product of:
                1.0 = tf(freq=1.0), with freq of:
                  1.0 = termFreq=1.0
                3.2269485 = idf(docFreq=4562, maxDocs=42306)
                0.078125 = fieldNorm(doc=4769)
          0.060938727 = weight(abstract_txt:similarity in 4769) [ClassicSimilarity], result of:
            0.060938727 = score(doc=4769,freq=2.0), product of:
              0.09485104 = queryWeight, product of:
                1.4648876 = boost
                5.814954 = idf(docFreq=342, maxDocs=42306)
                0.011135032 = queryNorm
              0.6424677 = fieldWeight in 4769, product of:
                1.4142135 = tf(freq=2.0), with freq of:
                  2.0 = termFreq=2.0
                5.814954 = idf(docFreq=342, maxDocs=42306)
                0.078125 = fieldNorm(doc=4769)
          0.18630257 = weight(abstract_txt:multidimensional in 4769) [ClassicSimilarity], result of:
            0.18630257 = score(doc=4769,freq=1.0), product of:
              0.34165075 = queryWeight, product of:
                4.3958664 = boost
                6.9798555 = idf(docFreq=106, maxDocs=42306)
                0.011135032 = queryNorm
              0.5453012 = fieldWeight in 4769, product of:
                1.0 = tf(freq=1.0), with freq of:
                  1.0 = termFreq=1.0
                6.9798555 = idf(docFreq=106, maxDocs=42306)
                0.078125 = fieldNorm(doc=4769)
          0.44222534 = weight(abstract_txt:scaling in 4769) [ClassicSimilarity], result of:
            0.44222534 = score(doc=4769,freq=4.0), product of:
              0.3829825 = queryWeight, product of:
                4.6541753 = boost
                7.390004 = idf(docFreq=70, maxDocs=42306)
                0.011135032 = queryNorm
              1.1546881 = fieldWeight in 4769, product of:
                2.0 = tf(freq=4.0), with freq of:
                  4.0 = termFreq=4.0
                7.390004 = idf(docFreq=70, maxDocs=42306)
                0.078125 = fieldNorm(doc=4769)
        0.2 = coord(5/25)
    
  2. Osiñska, V.: Visual analysis of classification scheme (2010) 0.15
    0.14582594 = sum of:
      0.14582594 = product of:
        0.6076081 = sum of:
          0.008836838 = weight(abstract_txt:these in 1069) [ClassicSimilarity], result of:
            0.008836838 = score(doc=1069,freq=1.0), product of:
              0.043815207 = queryWeight, product of:
                1.2193863 = boost
                3.2269485 = idf(docFreq=4562, maxDocs=42306)
                0.011135032 = queryNorm
              0.20168428 = fieldWeight in 1069, product of:
                1.0 = tf(freq=1.0), with freq of:
                  1.0 = termFreq=1.0
                3.2269485 = idf(docFreq=4562, maxDocs=42306)
                0.0625 = fieldNorm(doc=1069)
          0.04875098 = weight(abstract_txt:similarity in 1069) [ClassicSimilarity], result of:
            0.04875098 = score(doc=1069,freq=2.0), product of:
              0.09485104 = queryWeight, product of:
                1.4648876 = boost
                5.814954 = idf(docFreq=342, maxDocs=42306)
                0.011135032 = queryNorm
              0.51397413 = fieldWeight in 1069, product of:
                1.4142135 = tf(freq=2.0), with freq of:
                  2.0 = termFreq=2.0
                5.814954 = idf(docFreq=342, maxDocs=42306)
                0.0625 = fieldNorm(doc=1069)
          0.071671315 = weight(abstract_txt:maps in 1069) [ClassicSimilarity], result of:
            0.071671315 = score(doc=1069,freq=1.0), product of:
              0.19467196 = queryWeight, product of:
                2.967905 = boost
                5.8906326 = idf(docFreq=317, maxDocs=42306)
                0.011135032 = queryNorm
              0.36816454 = fieldWeight in 1069, product of:
                1.0 = tf(freq=1.0), with freq of:
                  1.0 = termFreq=1.0
                5.8906326 = idf(docFreq=317, maxDocs=42306)
                0.0625 = fieldNorm(doc=1069)
          0.15241675 = weight(abstract_txt:visualize in 1069) [ClassicSimilarity], result of:
            0.15241675 = score(doc=1069,freq=1.0), product of:
              0.32193014 = queryWeight, product of:
                3.8166215 = boost
                7.5751467 = idf(docFreq=58, maxDocs=42306)
                0.011135032 = queryNorm
              0.47344667 = fieldWeight in 1069, product of:
                1.0 = tf(freq=1.0), with freq of:
                  1.0 = termFreq=1.0
                7.5751467 = idf(docFreq=58, maxDocs=42306)
                0.0625 = fieldNorm(doc=1069)
          0.14904206 = weight(abstract_txt:multidimensional in 1069) [ClassicSimilarity], result of:
            0.14904206 = score(doc=1069,freq=1.0), product of:
              0.34165075 = queryWeight, product of:
                4.3958664 = boost
                6.9798555 = idf(docFreq=106, maxDocs=42306)
                0.011135032 = queryNorm
              0.43624097 = fieldWeight in 1069, product of:
                1.0 = tf(freq=1.0), with freq of:
                  1.0 = termFreq=1.0
                6.9798555 = idf(docFreq=106, maxDocs=42306)
                0.0625 = fieldNorm(doc=1069)
          0.17689013 = weight(abstract_txt:scaling in 1069) [ClassicSimilarity], result of:
            0.17689013 = score(doc=1069,freq=1.0), product of:
              0.3829825 = queryWeight, product of:
                4.6541753 = boost
                7.390004 = idf(docFreq=70, maxDocs=42306)
                0.011135032 = queryNorm
              0.46187526 = fieldWeight in 1069, product of:
                1.0 = tf(freq=1.0), with freq of:
                  1.0 = termFreq=1.0
                7.390004 = idf(docFreq=70, maxDocs=42306)
                0.0625 = fieldNorm(doc=1069)
        0.24 = coord(6/25)
    
  3. Eck, N.J. van; Waltman, L.; Dekker, R.; Berg, J. van den: ¬A comparison of two techniques for bibliometric mapping : multidimensional scaling and VOS (2010) 0.14
    0.1447948 = sum of:
      0.1447948 = product of:
        0.72397405 = sum of:
          0.053969838 = weight(abstract_txt:technique in 1113) [ClassicSimilarity], result of:
            0.053969838 = score(doc=1113,freq=2.0), product of:
              0.08747432 = queryWeight, product of:
                1.4067715 = boost
                5.5842586 = idf(docFreq=431, maxDocs=42306)
                0.011135032 = queryNorm
              0.61697924 = fieldWeight in 1113, product of:
                1.4142135 = tf(freq=2.0), with freq of:
                  2.0 = termFreq=2.0
                5.5842586 = idf(docFreq=431, maxDocs=42306)
                0.078125 = fieldNorm(doc=1113)
          0.043141246 = weight(abstract_txt:techniques in 1113) [ClassicSimilarity], result of:
            0.043141246 = score(doc=1113,freq=2.0), product of:
              0.086245954 = queryWeight, product of:
                1.7107962 = boost
                4.527401 = idf(docFreq=1242, maxDocs=42306)
                0.011135032 = queryNorm
              0.50021183 = fieldWeight in 1113, product of:
                1.4142135 = tf(freq=2.0), with freq of:
                  2.0 = termFreq=2.0
                4.527401 = idf(docFreq=1242, maxDocs=42306)
                0.078125 = fieldNorm(doc=1113)
          0.21944769 = weight(abstract_txt:maps in 1113) [ClassicSimilarity], result of:
            0.21944769 = score(doc=1113,freq=6.0), product of:
              0.19467196 = queryWeight, product of:
                2.967905 = boost
                5.8906326 = idf(docFreq=317, maxDocs=42306)
                0.011135032 = queryNorm
              1.1272691 = fieldWeight in 1113, product of:
                2.4494898 = tf(freq=6.0), with freq of:
                  6.0 = termFreq=6.0
                5.8906326 = idf(docFreq=317, maxDocs=42306)
                0.078125 = fieldNorm(doc=1113)
          0.18630257 = weight(abstract_txt:multidimensional in 1113) [ClassicSimilarity], result of:
            0.18630257 = score(doc=1113,freq=1.0), product of:
              0.34165075 = queryWeight, product of:
                4.3958664 = boost
                6.9798555 = idf(docFreq=106, maxDocs=42306)
                0.011135032 = queryNorm
              0.5453012 = fieldWeight in 1113, product of:
                1.0 = tf(freq=1.0), with freq of:
                  1.0 = termFreq=1.0
                6.9798555 = idf(docFreq=106, maxDocs=42306)
                0.078125 = fieldNorm(doc=1113)
          0.22111267 = weight(abstract_txt:scaling in 1113) [ClassicSimilarity], result of:
            0.22111267 = score(doc=1113,freq=1.0), product of:
              0.3829825 = queryWeight, product of:
                4.6541753 = boost
                7.390004 = idf(docFreq=70, maxDocs=42306)
                0.011135032 = queryNorm
              0.57734406 = fieldWeight in 1113, product of:
                1.0 = tf(freq=1.0), with freq of:
                  1.0 = termFreq=1.0
                7.390004 = idf(docFreq=70, maxDocs=42306)
                0.078125 = fieldNorm(doc=1113)
        0.2 = coord(5/25)
    
  4. Lund, K.; Burgess, C.; Atchley, R.A.: Semantic and associative priming in high-dimensional semantic space (1995) 0.14
    0.14336199 = sum of:
      0.14336199 = product of:
        0.7168099 = sum of:
          0.015464468 = weight(abstract_txt:these in 4152) [ClassicSimilarity], result of:
            0.015464468 = score(doc=4152,freq=1.0), product of:
              0.043815207 = queryWeight, product of:
                1.2193863 = boost
                3.2269485 = idf(docFreq=4562, maxDocs=42306)
                0.011135032 = queryNorm
              0.3529475 = fieldWeight in 4152, product of:
                1.0 = tf(freq=1.0), with freq of:
                  1.0 = termFreq=1.0
                3.2269485 = idf(docFreq=4562, maxDocs=42306)
                0.109375 = fieldNorm(doc=4152)
          0.07063783 = weight(abstract_txt:word in 4152) [ClassicSimilarity], result of:
            0.07063783 = score(doc=4152,freq=2.0), product of:
              0.083634615 = queryWeight, product of:
                1.3755498 = boost
                5.460322 = idf(docFreq=488, maxDocs=42306)
                0.011135032 = queryNorm
              0.84460044 = fieldWeight in 4152, product of:
                1.4142135 = tf(freq=2.0), with freq of:
                  2.0 = termFreq=2.0
                5.460322 = idf(docFreq=488, maxDocs=42306)
                0.109375 = fieldNorm(doc=4152)
          0.060326267 = weight(abstract_txt:similarity in 4152) [ClassicSimilarity], result of:
            0.060326267 = score(doc=4152,freq=1.0), product of:
              0.09485104 = queryWeight, product of:
                1.4648876 = boost
                5.814954 = idf(docFreq=342, maxDocs=42306)
                0.011135032 = queryNorm
              0.6360106 = fieldWeight in 4152, product of:
                1.0 = tf(freq=1.0), with freq of:
                  1.0 = termFreq=1.0
                5.814954 = idf(docFreq=342, maxDocs=42306)
                0.109375 = fieldNorm(doc=4152)
          0.2608236 = weight(abstract_txt:multidimensional in 4152) [ClassicSimilarity], result of:
            0.2608236 = score(doc=4152,freq=1.0), product of:
              0.34165075 = queryWeight, product of:
                4.3958664 = boost
                6.9798555 = idf(docFreq=106, maxDocs=42306)
                0.011135032 = queryNorm
              0.7634217 = fieldWeight in 4152, product of:
                1.0 = tf(freq=1.0), with freq of:
                  1.0 = termFreq=1.0
                6.9798555 = idf(docFreq=106, maxDocs=42306)
                0.109375 = fieldNorm(doc=4152)
          0.30955774 = weight(abstract_txt:scaling in 4152) [ClassicSimilarity], result of:
            0.30955774 = score(doc=4152,freq=1.0), product of:
              0.3829825 = queryWeight, product of:
                4.6541753 = boost
                7.390004 = idf(docFreq=70, maxDocs=42306)
                0.011135032 = queryNorm
              0.8082817 = fieldWeight in 4152, product of:
                1.0 = tf(freq=1.0), with freq of:
                  1.0 = termFreq=1.0
                7.390004 = idf(docFreq=70, maxDocs=42306)
                0.109375 = fieldNorm(doc=4152)
        0.2 = coord(5/25)
    
  5. White, H.D.: Pathfinder networks and author cocitation analysis : a remapping of paradigmatic information scientists (2003) 0.13
    0.13495995 = sum of:
      0.13495995 = product of:
        0.4819998 = sum of:
          0.012497176 = weight(abstract_txt:these in 2460) [ClassicSimilarity], result of:
            0.012497176 = score(doc=2460,freq=2.0), product of:
              0.043815207 = queryWeight, product of:
                1.2193863 = boost
                3.2269485 = idf(docFreq=4562, maxDocs=42306)
                0.011135032 = queryNorm
              0.28522465 = fieldWeight in 2460, product of:
                1.4142135 = tf(freq=2.0), with freq of:
                  2.0 = termFreq=2.0
                3.2269485 = idf(docFreq=4562, maxDocs=42306)
                0.0625 = fieldNorm(doc=2460)
          0.03052995 = weight(abstract_txt:technique in 2460) [ClassicSimilarity], result of:
            0.03052995 = score(doc=2460,freq=1.0), product of:
              0.08747432 = queryWeight, product of:
                1.4067715 = boost
                5.5842586 = idf(docFreq=431, maxDocs=42306)
                0.011135032 = queryNorm
              0.34901616 = fieldWeight in 2460, product of:
                1.0 = tf(freq=1.0), with freq of:
                  1.0 = termFreq=1.0
                5.5842586 = idf(docFreq=431, maxDocs=42306)
                0.0625 = fieldNorm(doc=2460)
          0.024404377 = weight(abstract_txt:techniques in 2460) [ClassicSimilarity], result of:
            0.024404377 = score(doc=2460,freq=1.0), product of:
              0.086245954 = queryWeight, product of:
                1.7107962 = boost
                4.527401 = idf(docFreq=1242, maxDocs=42306)
                0.011135032 = queryNorm
              0.28296256 = fieldWeight in 2460, product of:
                1.0 = tf(freq=1.0), with freq of:
                  1.0 = termFreq=1.0
                4.527401 = idf(docFreq=1242, maxDocs=42306)
                0.0625 = fieldNorm(doc=2460)
          0.016964804 = weight(abstract_txt:data in 2460) [ClassicSimilarity], result of:
            0.016964804 = score(doc=2460,freq=1.0), product of:
              0.08024336 = queryWeight, product of:
                2.1303837 = boost
                3.382671 = idf(docFreq=3904, maxDocs=42306)
                0.011135032 = queryNorm
              0.21141694 = fieldWeight in 2460, product of:
                1.0 = tf(freq=1.0), with freq of:
                  1.0 = termFreq=1.0
                3.382671 = idf(docFreq=3904, maxDocs=42306)
                0.0625 = fieldNorm(doc=2460)
          0.071671315 = weight(abstract_txt:maps in 2460) [ClassicSimilarity], result of:
            0.071671315 = score(doc=2460,freq=1.0), product of:
              0.19467196 = queryWeight, product of:
                2.967905 = boost
                5.8906326 = idf(docFreq=317, maxDocs=42306)
                0.011135032 = queryNorm
              0.36816454 = fieldWeight in 2460, product of:
                1.0 = tf(freq=1.0), with freq of:
                  1.0 = termFreq=1.0
                5.8906326 = idf(docFreq=317, maxDocs=42306)
                0.0625 = fieldNorm(doc=2460)
          0.14904206 = weight(abstract_txt:multidimensional in 2460) [ClassicSimilarity], result of:
            0.14904206 = score(doc=2460,freq=1.0), product of:
              0.34165075 = queryWeight, product of:
                4.3958664 = boost
                6.9798555 = idf(docFreq=106, maxDocs=42306)
                0.011135032 = queryNorm
              0.43624097 = fieldWeight in 2460, product of:
                1.0 = tf(freq=1.0), with freq of:
                  1.0 = termFreq=1.0
                6.9798555 = idf(docFreq=106, maxDocs=42306)
                0.0625 = fieldNorm(doc=2460)
          0.17689013 = weight(abstract_txt:scaling in 2460) [ClassicSimilarity], result of:
            0.17689013 = score(doc=2460,freq=1.0), product of:
              0.3829825 = queryWeight, product of:
                4.6541753 = boost
                7.390004 = idf(docFreq=70, maxDocs=42306)
                0.011135032 = queryNorm
              0.46187526 = fieldWeight in 2460, product of:
                1.0 = tf(freq=1.0), with freq of:
                  1.0 = termFreq=1.0
                7.390004 = idf(docFreq=70, maxDocs=42306)
                0.0625 = fieldNorm(doc=2460)
        0.28 = coord(7/25)