arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1803.01900cs.NE
收藏

风格记忆:使分类器网络具有生成性

Style Memory: Making a Classifier Network Generative

Rey Wiyatno, Jeff Orchard

摘要:

深度网络在分类任务中表现出了出色的性能。然而,由分类器网络学习的参数通常丢弃输入的风格信息,而支持与分类严格相关的信息。我们引入了一个网络,有能力做分类和重建,通过添加一个“风格记忆”的网络的输出层。我们还展示了如何训练这样的神经网络作为一个深多层自动编码器,共同最大限度地减少分类和重建损失。我们的网络的生成能力表明,当分类正确时,风格记忆神经元与分类器神经元的组合会产生良好的输入重建。我们进一步研究了风格记忆的本质,以及它与数字和字母的构成之间的关系。最后,我们提出,这种架构可以实现预测编码中使用的双向信息流,并且这种双向网络可以帮助减轻被模糊或对抗性输入愚弄的风险。

英文摘要:

Deep networks have shown great performance in classification tasks. However, the parameters learned by the classifier networks usually discard stylistic information of the input, in favour of information strictly relevant to classification. We introduce a network that has the capacity to do both classification and reconstruction by adding a "style memory" to the output layer of the network. We also show how to train such a neural network as a deep multi-layer autoencoder, jointly minimizing both classification and reconstruction losses. The generative capacity of our network demonstrates that the combination of style-memory neurons with the classifier neurons yield good reconstructions of the inputs when the classification is correct. We further investigate the nature of the style memory, and how it relates to composing digits and letters. Finally, we propose that this architecture enables the bidirectional flow of information used in predictive coding, and that such bidirectional networks can help mitigate against being fooled by ambiguous or adversarial input.

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。

↑