Search (2 results, page 1 of 1)

0.02382353 = product of:
  0.04764706 = sum of:
    0.04764706 = product of:
      0.09529412 = sum of:
        0.09529412 = weight(_text_:t in 3888) [ClassicSimilarity], result of:
          0.09529412 = score(doc=3888,freq=12.0), product of:
            0.17876579 = queryWeight, product of:
              3.9394085 = idf(docFreq=2338, maxDocs=44218)
              0.04537884 = queryNorm
            0.53306687 = fieldWeight in 3888, product of:
              3.4641016 = tf(freq=12.0), with freq of:
                12.0 = termFreq=12.0
              3.9394085 = idf(docFreq=2338, maxDocs=44218)
              0.0390625 = fieldNorm(doc=3888)
      0.5 = coord(1/2)
  0.5 = coord(1/2)

Abstract

We present a new technique called "t-SNE" that visualizes high-dimensional data by giving each datapoint a location in a two or three-dimensional map. The technique is a variation of Stochastic Neighbor Embedding (Hinton and Roweis, 2002) that is much easier to optimize, and produces significantly better visualizations by reducing the tendency to crowd points together in the center of the map. t-SNE is better than existing techniques at creating a single map that reveals structure at many different scales. This is particularly important for high-dimensional data that lie on several different, but related, low-dimensional manifolds, such as images of objects from multiple classes seen from multiple viewpoints. For visualizing the structure of very large data sets, we show how t-SNE can use random walks on neighborhood graphs to allow the implicit structure of all of the data to influence the way in which a subset of the data is displayed. We illustrate the performance of t-SNE on a wide variety of data sets and compare it with many other non-parametric visualization techniques, including Sammon mapping, Isomap, and Locally Linear Embedding. The visualizations produced by t-SNE are significantly better than those produced by the other techniques on almost all of the data sets.

0.020214936 = product of:
  0.04042987 = sum of:
    0.04042987 = product of:
      0.08085974 = sum of:
        0.08085974 = weight(_text_:t in 3884) [ClassicSimilarity], result of:
          0.08085974 = score(doc=3884,freq=6.0), product of:
            0.17876579 = queryWeight, product of:
              3.9394085 = idf(docFreq=2338, maxDocs=44218)
              0.04537884 = queryNorm
            0.45232224 = fieldWeight in 3884, product of:
              2.4494898 = tf(freq=6.0), with freq of:
                6.0 = termFreq=6.0
              3.9394085 = idf(docFreq=2338, maxDocs=44218)
              0.046875 = fieldNorm(doc=3884)
      0.5 = coord(1/2)
  0.5 = coord(1/2)

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.