Tiven Wang
Wang Tiven July 31, 2018
425 favorite favorites
bookmark bookmark
share share

Recurrent Neural Networks

Embeddings

An embedding is a relatively low-dimensional space into which you can translate high-dimensional vectors.

TensorFlow Guide - Embeddings

Crash Course - Embeddings

Principal component analysis (PCA) is a statistical procedure that uses an orthogonal transformation to convert a set of observations of possibly correlated variables into a set of values of linearly uncorrelated variables called principal components.

在多元统计分析中,主成分分析( Principal components analysis, PCA )是一种分析、简化数据集的技术。主成分分析经常用于减少数据集的维数,同时保持数据集中的对方差贡献最大的特征。这是通过保留低阶主成分,忽略高阶主成分做到的。这样低阶成分往往能够保留住数据的最重要方面。但是,这也不是一定的,要视具体应用而定。由于主成分分析依赖所给数据,所以数据的准确性对分析结果影响很大。

http://colah.github.io/posts/2014-10-Visualizing-MNIST/

https://github.com/rmeertens/Simplest-Tensorflow-Tensorboard-MNIST-Embedding-Visualisation/blob/master/Minimal%20example%20embeddings.ipynb

References

Similar Posts

Comments

Back to Top