arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1409.7461cs.LGstat.ML
收藏

自动编码器树

Autoencoder Trees

Cornell University(康奈尔大学);Boğaziçi University(海峡大学)

Ozan İrsoy, Ethem Alpaydın

摘要:

我们讨论了一个自动编码器模型,其中的编码和解码功能的决策树实现。我们使用软决策树,其中内部节点实现由选通函数给出的软多变量分裂,并且总体输出是由其路径上的选通值加权的所有叶子的平均值。编码器树接受输入并在叶子中生成低维表示,解码器树接受该表示并重建原始输入。利用树的连续性,用随机梯度下降训练自动编码器树。在手写数字和新闻数据上,我们看到与传统的自动编码感知器相比,自动编码器树产生了良好的重建误差。我们还看到,自动编码器树在其不同级别上捕获数据的不同粒度的分层表示,而叶子捕获输入空间中的位置。

英文摘要:

We discuss an autoencoder model in which the encoding and decoding functions are implemented by decision trees. We use the soft decision tree where internal nodes realize soft multivariate splits given by a gating function and the overall output is the average of all leaves weighted by the gating values on their path. The encoder tree takes the input and generates a lower dimensional representation in the leaves and the decoder tree takes this and reconstructs the original input. Exploiting the continuity of the trees, autoencoder trees are trained with stochastic gradient descent. On handwritten digit and news data, we see that the autoencoder trees yield good reconstruction error compared to traditional autoencoder perceptrons. We also see that the autoencoder tree captures hierarchical representations at different granularities of the data on its different levels and the leaves capture the localities in the input space.

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。

↑