å˜èªžãƒ»å¥ã®åˆ†æ•£è¡¨ç¾ã®å¦ç¿’[DL輪èªä¼š]Grokking: Generalization Beyond Overfitting on Small Algorithmic Datasets
高次元データã®æ¬¡å…ƒå‰Šæ¸›ãŠã‚ˆã³2次元プãƒãƒƒãƒˆæ‰‹æ³• - Qiita
ã¯ã˜ã‚㫠本記事ã¯Python2.7, numpy 1.11, scipy 0.17, scikit-learn 0.18, matplotlib 1.5, seaborn 0.7, pandas 0.17を使用ã—ã¦ã„ã¾ã™ï¼Ž jupyter notebook上ã§å‹•ä½œç¢ºèªæ¸ˆã¿ã§ã™ï¼Ž(%matplotlib inlineã¯é©å½“ã«ä¿®æ£ã—ã¦ãã ã•ã„) Sklearnã®Manifold learningã®è¨˜äº‹ã‚’å‚考ã«ã—ã¦ã„ã¾ã™ï¼Ž 多様体å¦ç¿’ã¨è¨€ã‚れる手法ã«ã¤ã„ã¦ï¼Œsklearnã®digitsサンプルを用ã„ã¦èª¬æ˜Žã—ã¾ã™ï¼Ž 特ã«t-SNEã¯Kaggleãªã©ã§ã‚‚ãŸã¾ã«ä½¿ç”¨ã•ã‚Œã¦ã„る，多次元データã®å¯è¦–化ã«é©ã—ãŸæ‰‹æ³•ã§ã™ï¼Ž ã¾ãŸå¯è¦–化ã ã‘ã§ãªã，元ã®ãƒ‡ãƒ¼ã‚¿ã¨åœ§ç¸®ã•ã‚ŒãŸãƒ‡ãƒ¼ã‚¿ã‚’çµåˆã™ã‚‹ã“ã¨ã§ï¼Œå˜ç´”ãªåˆ†é¡žå•é¡Œã®ç²¾åº¦ã‚’å‘上ã™ã‚‹ã“ã¨ãŒã§ãã¾ã™ï¼Ž 目次 データã®ç”Ÿæˆ ç·šå½¢è¦ç´ ã«æ³¨ç›®ã—ãŸæ¬¡å…ƒå‰Šæ¸› Random Proj
t-SNE
t-Distributed Stochastic Neighbor Embedding (t-SNE) is a technique for dimensionality reduction that is particularly well suited for the visualization of high-dimensional datasets. The technique can be implemented via Barnes-Hut approximations, allowing it to be applied on large real-world datasets. We applied it on data sets with up to 30 million examples. The technique and its variants are intro
Locally Linear Embedding (LLE) Homepage
(Notes, e.g. [a] appear below) Input X: D by N matrix consisting of N data items in D dimensions. Output Y: d by N matrix consisting of d < D dimensional embedding coordinates for the input points. Find neighbours in X space [b,c]. for i=1:N compute the distance from Xi to every other point Xj find the K smallest distances assign the corresponding points to be neighbours of Xi end Solve for recons
1
ランã‚ング
ランã‚ング
ãŠçŸ¥ã‚‰ã›
リリースã€éšœå®³æƒ…å ±ãªã©ã®ã‚µãƒ¼ãƒ“スã®ãŠçŸ¥ã‚‰ã›
最新ã®äººæ°—エントリーã®é…ä¿¡
処ç†ã‚’実行ä¸ã§ã™
j次ã®ãƒ–ックマーク
kå‰ã®ãƒ–ックマーク
lã‚ã¨ã§èªã‚€
eコメント一覧を開ã
oページを開ã
GitHub - rksltnl/Deep-Metric-Learning-CVPR16: Main repository for Deep Metric Learning via Lifted Structured Feature Embedding
{{#tags}}- {{label}}
{{/tags}}