|
1 |
| -- abstract': >- |
| 1 | +- abstract'@: >- |
| 2 | + We present a new technique called “t-SNE” that visualizes |
| 3 | + high-dimensional data by giving each datapoint a location in a two |
| 4 | + or three-dimensional map. The technique is a variation of Stochastic |
| 5 | + Neighbor Embedding {[}@hinton:stochastic{]} that is much easier to |
| 6 | + optimize, and produces significantly better visualizations by |
| 7 | + reducing the tendency to crowd points together in the center of the |
| 8 | + map. t-SNE is better than existing techniques at creating a single |
| 9 | + map that reveals structure at many different scales. This is |
| 10 | + particularly important for high-dimensional data that lie on several |
| 11 | + different, but related, low-dimensional manifolds, such as images of |
| 12 | + objects from multiple classes seen from multiple viewpoints. For |
| 13 | + visualizing the structure of very large data sets, we show how t-SNE |
| 14 | + can use random walks on neighborhood graphs to allow the implicit |
| 15 | + structure of all the data to influence the way in which a subset of |
| 16 | + the data is displayed. We illustrate the performance of t-SNE on a |
| 17 | + wide variety of data sets and compare it with many other |
| 18 | + non-parametric visualization techniques, including Sammon mapping, |
| 19 | + Isomap, and Locally Linear Embedding. The visualization produced by |
| 20 | + t-SNE are significantly better than those produced by other |
| 21 | + techniques on almost all of the data sets. |
| 22 | + authors@: Laurens van der Maaten and Geoffrey Hinton |
| 23 | + bibtex@: >+ |
| 24 | + @article{van_der_maaten2008, |
| 25 | + author = {van der Maaten, Laurens and Hinton, Geoffrey}, |
| 26 | + publisher = {French Statistical Society}, |
| 27 | + title = {Visualizing {Data} Using {t-SNE} (Mock Contributon)}, |
| 28 | + journal = {Computo}, |
| 29 | + date = {2008-08-11}, |
| 30 | + doi = {10.57750/xxxxxx}, |
| 31 | + issn = {2824-7795}, |
| 32 | + langid = {en}, |
| 33 | + abstract = {We present a new technique called “t-SNE” that visualizes |
| 34 | + high-dimensional data by giving each datapoint a location in a two |
| 35 | + or three-dimensional map. The technique is a variation of Stochastic |
| 36 | + Neighbor Embedding {[}@hinton:stochastic{]} that is much easier to |
| 37 | + optimize, and produces significantly better visualizations by |
| 38 | + reducing the tendency to crowd points together in the center of the |
| 39 | + map. t-SNE is better than existing techniques at creating a single |
| 40 | + map that reveals structure at many different scales. This is |
| 41 | + particularly important for high-dimensional data that lie on several |
| 42 | + different, but related, low-dimensional manifolds, such as images of |
| 43 | + objects from multiple classes seen from multiple viewpoints. For |
| 44 | + visualizing the structure of very large data sets, we show how t-SNE |
| 45 | + can use random walks on neighborhood graphs to allow the implicit |
| 46 | + structure of all the data to influence the way in which a subset of |
| 47 | + the data is displayed. We illustrate the performance of t-SNE on a |
| 48 | + wide variety of data sets and compare it with many other |
| 49 | + non-parametric visualization techniques, including Sammon mapping, |
| 50 | + Isomap, and Locally Linear Embedding. The visualization produced by |
| 51 | + t-SNE are significantly better than those produced by other |
| 52 | + techniques on almost all of the data sets.} |
| 53 | + } |
| 54 | +
|
| 55 | + date@: 2008-08-11 |
| 56 | + description@: > |
| 57 | + This page is a reworking of the original t-SNE article using the Computo template. It aims to help authors submitting to the journal by using some advanced formatting features. We warmly thank the authors of t-SNE and the editor of JMLR for allowing us to use their work to illustrate the Computo spirit. |
| 58 | + doi@: 10.57750/xxxxxx |
| 59 | + draft@: false |
| 60 | + journal@: Computo |
| 61 | + pdf@: '' |
| 62 | + repo@: published-paper-tsne |
| 63 | + title@: Visualizing Data using t-SNE (mock contributon) |
| 64 | + url@: '' |
| 65 | + year@: 2008 |
| 66 | + abstract': >- |
2 | 67 | We present a new technique called “t-SNE” that visualizes
|
3 | 68 | high-dimensional data by giving each datapoint a location in a two
|
4 | 69 | or three-dimensional map. The technique is a variation of Stochastic
|
|
23 | 88 | bibtex: >+
|
24 | 89 | @article{van_der_maaten2008,
|
25 | 90 | author = {van der Maaten, Laurens and Hinton, Geoffrey},
|
26 |
| - publisher = {Société Française de Statistique}, |
27 |
| - title = {Visualizing {Data} Using {t-SNE:} A Practical Computo Example |
28 |
| - (Mock)}, |
| 91 | + publisher = {French Statistical Society}, |
| 92 | + title = {Visualizing {Data} Using {t-SNE} (Mock Contributon)}, |
29 | 93 | journal = {Computo},
|
30 | 94 | date = {2008-08-11},
|
31 |
| - url = {https://computo.sfds.asso.fr/published-paper-tsne}, |
| 95 | + doi = {10.57750/xxxxxx}, |
32 | 96 | issn = {2824-7795},
|
33 | 97 | langid = {en},
|
34 | 98 | abstract = {We present a new technique called “t-SNE” that visualizes
|
|
56 | 120 | date: 2008-08-11
|
57 | 121 | description: >
|
58 | 122 | This page is a reworking of the original t-SNE article using the Computo template. It aims to help authors submitting to the journal by using some advanced formatting features. We warmly thank the authors of t-SNE and the editor of JMLR for allowing us to use their work to illustrate the Computo spirit.
|
59 |
| - doi: '' |
| 123 | + doi: 10.57750/xxxxxx |
60 | 124 | draft: false
|
61 | 125 | journal: Computo
|
62 | 126 | pdf: ''
|
63 | 127 | repo: published-paper-tsne
|
64 | 128 | title: Visualizing Data using t-SNE (mock contributon)
|
65 |
| - url: https://computo-journal.org/published-paper-tsne |
| 129 | + url: '' |
66 | 130 | year: 2008
|
67 |
| -- abstract': >- |
| 131 | +- abstract'@: >- |
| 132 | + We present a new technique called “t-SNE” that visualizes |
| 133 | + high-dimensional data by giving each datapoint a location in a two |
| 134 | + or three-dimensional map. The technique is a variation of Stochastic |
| 135 | + Neighbor Embeddi{[}@hinton:stochastic{]} that is much easier to |
| 136 | + optimize, and produces significantly better visualizations by |
| 137 | + reducing the tendency to crowd points together in the center of the |
| 138 | + map. t-SNE is better than existing techniques at creating a single |
| 139 | + map that reveals structure at many different scales. This is |
| 140 | + particularly important for high-dimensional data that lie on several |
| 141 | + different, but related, low-dimensional manifolds, such as images of |
| 142 | + objects from multiple classes seen from multiple viewpoints. For |
| 143 | + visualizing the structure of very large data sets, we show how t-SNE |
| 144 | + can use random walks on neighborhood graphs to allow the implicit |
| 145 | + structure of all the data to influence the way in which a subset of |
| 146 | + the data is displayed. We illustrate the performance of t-SNE on a |
| 147 | + wide variety of data sets and compare it with many other |
| 148 | + non-parametric visualization techniques, including Sammon mapping, |
| 149 | + Isomap, and Locally Linear Embedding. The visualization produced by |
| 150 | + t-SNE are significantly better than those produced by other |
| 151 | + techniques on almost all of the data sets. |
| 152 | + authors@: Laurens van der Maaten and Geoffrey Hinton |
| 153 | + bibtex@: >+ |
| 154 | + @article{van_der_maaten2008, |
| 155 | + author = {van der Maaten, Laurens and Hinton, Geoffrey}, |
| 156 | + publisher = {French Statistical Society}, |
| 157 | + title = {Visualizing {Data} Using {t-SNE} (Mock Contributon)}, |
| 158 | + journal = {Computo}, |
| 159 | + date = {2008-08-11}, |
| 160 | + doi = {10.57750/xxxxxx}, |
| 161 | + issn = {2824-7795}, |
| 162 | + langid = {en}, |
| 163 | + abstract = {We present a new technique called “t-SNE” that visualizes |
| 164 | + high-dimensional data by giving each datapoint a location in a two |
| 165 | + or three-dimensional map. The technique is a variation of Stochastic |
| 166 | + Neighbor Embeddi{[}@hinton:stochastic{]} that is much easier to |
| 167 | + optimize, and produces significantly better visualizations by |
| 168 | + reducing the tendency to crowd points together in the center of the |
| 169 | + map. t-SNE is better than existing techniques at creating a single |
| 170 | + map that reveals structure at many different scales. This is |
| 171 | + particularly important for high-dimensional data that lie on several |
| 172 | + different, but related, low-dimensional manifolds, such as images of |
| 173 | + objects from multiple classes seen from multiple viewpoints. For |
| 174 | + visualizing the structure of very large data sets, we show how t-SNE |
| 175 | + can use random walks on neighborhood graphs to allow the implicit |
| 176 | + structure of all the data to influence the way in which a subset of |
| 177 | + the data is displayed. We illustrate the performance of t-SNE on a |
| 178 | + wide variety of data sets and compare it with many other |
| 179 | + non-parametric visualization techniques, including Sammon mapping, |
| 180 | + Isomap, and Locally Linear Embedding. The visualization produced by |
| 181 | + t-SNE are significantly better than those produced by other |
| 182 | + techniques on almost all of the data sets.} |
| 183 | + } |
| 184 | +
|
| 185 | + date@: 2008-08-11 |
| 186 | + description@: > |
| 187 | + This page is a reworking of the original t-SNE article using the Computo template. It aims to help authors submitting to the journal by using some advanced formatting features. We warmly thank the authors of t-SNE and the editor of JMLR for allowing us to use their work to illustrate the Computo spirit. |
| 188 | + doi@: 10.57750/xxxxxx |
| 189 | + draft@: false |
| 190 | + journal@: Computo |
| 191 | + pdf@: '' |
| 192 | + repo@: published-paper-tsne-R |
| 193 | + title@: Visualizing Data using t-SNE (mock contributon) |
| 194 | + url@: '' |
| 195 | + year@: 2008 |
| 196 | + abstract': >- |
68 | 197 | We present a new technique called “t-SNE” that visualizes
|
69 | 198 | high-dimensional data by giving each datapoint a location in a two
|
70 | 199 | or three-dimensional map. The technique is a variation of Stochastic
|
|
90 | 219 | @article{van_der_maaten2008,
|
91 | 220 | author = {van der Maaten, Laurens and Hinton, Geoffrey},
|
92 | 221 | publisher = {French Statistical Society},
|
93 |
| - title = {Visualizing {Data} Using {t-SNE:} A Practical {Computo} |
94 |
| - Example (Mock)}, |
| 222 | + title = {Visualizing {Data} Using {t-SNE} (Mock Contributon)}, |
95 | 223 | journal = {Computo},
|
96 | 224 | date = {2008-08-11},
|
97 |
| - url = {https://computo-journal.org/published-paper-tsne-R}, |
| 225 | + doi = {10.57750/xxxxxx}, |
98 | 226 | issn = {2824-7795},
|
99 | 227 | langid = {en},
|
100 | 228 | abstract = {We present a new technique called “t-SNE” that visualizes
|
|
122 | 250 | date: 2008-08-11
|
123 | 251 | description: >
|
124 | 252 | This page is a reworking of the original t-SNE article using the Computo template. It aims to help authors submitting to the journal by using some advanced formatting features. We warmly thank the authors of t-SNE and the editor of JMLR for allowing us to use their work to illustrate the Computo spirit.
|
125 |
| - doi: '' |
| 253 | + doi: 10.57750/xxxxxx |
126 | 254 | draft: false
|
127 | 255 | journal: Computo
|
128 | 256 | pdf: ''
|
129 | 257 | repo: published-paper-tsne-R
|
130 | 258 | title: Visualizing Data using t-SNE (mock contributon)
|
131 |
| - url: https://computo-journal.org/published-paper-tsne-R |
| 259 | + url: '' |
132 | 260 | year: 2008
|
0 commit comments