arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1909.13327q-bio.QMcs.LGstat.ML
收藏

使用复制的自动编码器自然表示复合数据

Natural representation of composite data with replicated autoencoders

Politecnico di Torino(都灵理工大学);Bocconi University(博科尼大学)

Matteo Negri, Davide Bergamini, Carlo Baldassi, Riccardo Zecchina, Christoph Feinauer

摘要:

生物学和其他领域的生成过程经常产生可以被视为由基本特征组合而成的数据。在这里,我们提出了一种基于自动编码器的无监督方法,用于推断数据的这些基本特征。我们的方法的主要新颖之处在于,训练是基于“局部熵”的优化,而不是标准损失,从而产生更强大的推理,并大大提高了这种类型的数据的性能。在数学上,这是通过训练复制的自动编码器的交互系统来实现的。我们将这种方法应用于合成和蛋白质序列数据,并表明它能够推断出一个隐藏的表示,以及相关的基本生成过程,而不需要任何先验知识。

英文摘要:

Generative processes in biology and other fields often produce data that can be regarded as resulting from a composition of basic features. Here we present an unsupervised method based on autoencoders for inferring these basic features of data. The main novelty in our approach is that the training is based on the optimization of the `local entropy' rather than the standard loss, resulting in a more robust inference, and enhancing the performance on this type of data considerably. Algorithmically, this is realized by training an interacting system of replicated autoencoders. We apply this method to synthetic and protein sequence data, and show that it is able to infer a hidden representation that correlates well with the underlying generative process, without requiring any prior knowledge.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑