Neural Architecture Search with Reinforcement Learning
Neural Architecture Search with Reinforcement Learning
复制标题
DOI：
--
复制
发表时间：
2016-11
期刊：
影响因子：
--
通讯作者：
Barret Zoph;Quoc V. Le
中科院分区：
文献类型：
--
作者：
Barret Zoph;Quoc V. Le
神经网络是强大而灵活的模型，可以很好地适用于图像，语音和自然语言理解中的许多困难学习任务。尽管他们成功了，但神经网络仍然很难设计。在本文中，我们使用一个经常性网络来生成神经网络的模型描述，并通过加强学习来训练此RNN，以最大程度地提高验证集中生成的体系结构的预期准确性。在CIFAR-10数据集上，从头开始，我们的方法可以设计出一种新颖的网络体系结构，该网络体系结构就测试集精度而言是最好的人类发明体系结构。我们的CIFAR-10模型达到的测试错误率为3.65，比使用类似的体系结构方案的先前最先进的模型要高0.09％和1.05倍。在Penn Treebank数据集上，我们的模型可以构成一个新颖的复发单元，该细胞的表现优于广泛使用的LSTM单元和其他最先进的基线。我们的单元格在宾夕法尼亚州立大学的测试集的困惑中达到了62.4的困惑，比以前的最新模型好3.6的困惑。该单元格也可以转移到PTB上的字符语言建模任务，并达到1.214的最新困惑。
Neural networks are powerful and flexible models that work well for many difficult learning tasks in image, speech and natural language understanding. Despite their success, neural networks are still hard to design. In this paper, we use a recurrent network to generate the model descriptions of neural networks and train this RNN with reinforcement learning to maximize the expected accuracy of the generated architectures on a validation set. On the CIFAR-10 dataset, our method, starting from scratch, can design a novel network architecture that rivals the best human-invented architecture in terms of test set accuracy. Our CIFAR-10 model achieves a test error rate of 3.65, which is 0.09 percent better and 1.05x faster than the previous state-of-the-art model that used a similar architectural scheme. On the Penn Treebank dataset, our model can compose a novel recurrent cell that outperforms the widely-used LSTM cell, and other state-of-the-art baselines. Our cell achieves a test set perplexity of 62.4 on the Penn Treebank, which is 3.6 perplexity better than the previous state-of-the-art model. The cell can also be transferred to the character language modeling task on PTB and achieves a state-of-the-art perplexity of 1.214.