Latent Space and Autoencoders (AE)

潜在空间是指LDA算法发现的话题向量所在的矢量空间,这些话题潜藏在文本中,需要通过算法揭示。自动编码器由编码器和解码器组成,数据在瓶颈层的压缩表示即为潜在空间,网络通过学习提取关键特征以重构输入。
摘要由CSDN通过智能技术生成

The "Latent Space" is the vector space within which the vectors that make up the topics found by LDA are found. These topics are latent within the text - that is, they are not immediately apparent, but are found or discovered by the LDA algorithm.

 

 

https://hackernoon.com/latent-space-visualization-deep-learning-bits-2-bd09a46920df?gi=44964379e8c8

What’s the latent space ?

An autoencoder is made of two components, here’s a quick reminder. The encoder brings the data from a high dimensional input to a bottleneck layer, where the number of neurons is the smallest. Then, the decoder takes this encoded input and converts it back to the original inp

评论
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值